大学 × Machine Learning
東京大学
Machine Learning / 2022–2026 LIVE
掲載論文 413 本
論文一覧
413 本
このEditionのランキングに掲載している論文です。同じ大学の複数著者による共著は1本にまとめています。
ランキングの対象論文 413 本と一致しています。
2026年
- A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
掲載ID:
pmlr:v336:chase26a - Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
掲載ID:
pmlr:v336:lee26a - Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret
掲載ID:
pmlr:v336:ito26a - A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
掲載ID:
iclr:2026:58c57ea0a02133f5844e89f662b28301 - Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
掲載ID:
iclr:2026:cbffadf96101c42be845d3e275c4b7e9 - Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners
掲載ID:
iclr:2026:ca0a348ce13a8cabbee9031112743776 - Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
掲載ID:
iclr:2026:1f961dc9f56c8cdb125438888de7d60e - Bilateral Information-aware Test-time Adaptation for Vision-Language Models
掲載ID:
iclr:2026:6454dcd80b5373daaa97e53ce32c78a1 - BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
掲載ID:
iclr:2026:d4e8355bcc5ac0a8b30aaac05fccc1f6 - C-Voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
掲載ID:
iclr:2026:e31c16c7b3e0ccee5159ae5443154fac - CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Vision-Language Model
掲載ID:
iclr:2026:0d66b749c9dadccb5dd0bcf17ea22a78 - Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
掲載ID:
iclr:2026:24a0f56452202e8433d582dbf5095c32 - Decoupling the Class Label and the Target Concept in Machine Unlearning
掲載ID:
iclr:2026:3327377ee37b8c87c43a7d6a4ea3d279 - DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Tree-based Search
掲載ID:
iclr:2026:9a583178bd18b2e55095c3a53f8fe88a - Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
掲載ID:
iclr:2026:6b5a158e43311d99728abdfdfe22a038 - Does “Do Differentiable Simulators Give Better Policy Gradients?” Give Better Policy Gradients?
掲載ID:
iclr:2026:4f0a2a0b2ca6ffd5c8d5de26d3e8d54d - Dynamical properties of dense associative memory
掲載ID:
iclr:2026:21a57aa30ccfec4e2b12ac122b1da7b3 - EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements
掲載ID:
iclr:2026:0e22eef358cd1d2bdb227e6b832cc775 - ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
掲載ID:
iclr:2026:829300b183943850930c3ce36fe04268 - EgoBrain: Synergizing Minds and Eyes For Human Action Understanding
掲載ID:
iclr:2026:96214e53d0ca519b0236a189bd3b6a18 - Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
掲載ID:
iclr:2026:af5509c72a244497c999ac39ba068ff4 - Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
掲載ID:
iclr:2026:9741242531c51c65aada05b5cb6d5c33 - Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
掲載ID:
iclr:2026:7eeb42802d3750ca59e8a0523068e9e6 - Fewer Weights, More Problems: A Practical Attack on LLM Pruning
掲載ID:
iclr:2026:36d981d89209558e4875372b95854e9f - Follow-Your-Preference: Towards Preference-Aligned Image Inpainting
掲載ID:
iclr:2026:f0ee2d0cb0c52844c907705c28ec08a5 - LFQA-E: Carefully Benchmarking Long-form QA Evaluation
掲載ID:
iclr:2026:90bacd92e0e887fd7ec3e95313442cda - Learning from Label Proportions via Proportional Value Classification
掲載ID:
iclr:2026:6fc46679a7ba2ec82183cf01b80e5133 - Mechanism of Task-oriented Information Removal in In-context Learning
掲載ID:
iclr:2026:105112d52254f86d5854f3da734a52b4 - Multiplayer Nash Preference Optimization
掲載ID:
iclr:2026:63796148c99205adb0fcac069cc714d4 - Neuron-Level Analysis of Cultural Understanding in Large Language Models
掲載ID:
iclr:2026:d50110d749bb4b1a92baec3481655512 - Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
掲載ID:
iclr:2026:8aa0c4d28021c0b273480f9e2aab83a6 - ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networks
掲載ID:
iclr:2026:aebec8058f23a445353c83ede0e1ec48 - Practical estimation of the optimal classification error with soft labels and calibration
掲載ID:
iclr:2026:039ef7b5decebab3145f7691b4708fe5 - Quantization-Aware Diffusion Models For Maximum Likelihood Training
掲載ID:
iclr:2026:55b1f861802e5f474cc630d7d8a17b31 - R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
掲載ID:
iclr:2026:d79ac139911df25d27f14bbf008deaee - RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
掲載ID:
iclr:2026:e52554a70e0df57a0bea11d1eca0c9b5 - Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
掲載ID:
iclr:2026:4f421415853c3a98c0cd311adeea4bd6 - Representation Alignment for Diffusion Transformers without External Components
掲載ID:
iclr:2026:201e691e8a0940291dc591eb0439a789 - Rethinking Consistent Multi-Label Classification Under Inexact Supervision
掲載ID:
iclr:2026:a7c1a61d395611ccfd9672b35720f102 - Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning
掲載ID:
iclr:2026:a597efe55fbf28afdd4d3f29a0e5fc3b - Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition
掲載ID:
iclr:2026:494ad6d9b36d9a1528dbf3baeb4e8a72 - SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNING
掲載ID:
iclr:2026:86178c06fd59ebc58dc31f8edb3c54af - SONA: Learning Conditional, Unconditional, and Matching-Aware Discriminator
掲載ID:
iclr:2026:6ad5d39b10e37915d7dfda2893d8e924 - Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
掲載ID:
iclr:2026:ec370e882e8a02be955679ddbd2731b8 - Smooth Calibration Error: Uniform Convergence and Functional Gradient Analysis
掲載ID:
iclr:2026:00a5213b3479c9733eb3743459badc6b - Submodular Function Minimization with Dueling Oracle
掲載ID:
iclr:2026:45d0b8e7ec7b52d960a1c7b43fdccac9 - Towards Scalable Oversight via Partitioned Human Supervision
掲載ID:
iclr:2026:b6f03ce953cf7f07dafa20891d2539e3 - Towards Understanding Valuable Preference Data for Large Language Model Alignment
掲載ID:
iclr:2026:2a7e91c6e4b68325d9884a7469804837 - Training-Free Determination of Network Width via Neural Tangent Kernel
掲載ID:
iclr:2026:38853020527b0f84187870114ff7a686 - TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models
掲載ID:
iclr:2026:c361ae924c23cafca6033610d25dbc65 - Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
掲載ID:
iclr:2026:c44c4afd77d5ee760e7f4bed0c50f878 - Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
掲載ID:
iclr:2026:7514354a089c7df0d9746c0c4ae759f2 - Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label Classification
掲載ID:
iclr:2026:cb825b4e5d0665a339e8d1aa08d1ca7e - Weak-to-Strong Diffusion with Reflection
掲載ID:
iclr:2026:607864303db1f2bea942b4a9d462920c - A Formal Comparison Between Chain of Thought and Latent Thought
掲載ID:
openreview:d6bqyajwmj - A Perturbation Approach to Unconstrained Linear Bandits
掲載ID:
openreview:xspbshzjag - Bridging Spherical Black-Box Optimizers
掲載ID:
openreview:x9ykvwz7if - CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting
掲載ID:
openreview:ocnt5pcmsq - Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting
掲載ID:
openreview:ojrisofudq - Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
掲載ID:
openreview:kovefbsxbq - Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
掲載ID:
openreview:cedywcrjoc - Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
掲載ID:
openreview:mcsbf1sm4p - Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
掲載ID:
openreview:ffahl32wok - Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
掲載ID:
openreview:uyriojfgon - Dichotomy of Feature Learning and Unlearning: Fast-Slow Analysis on Neural Networks with Stochastic Gradient Descent
掲載ID:
openreview:wg02gn1ygj - Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks
掲載ID:
openreview:pvafeunnsd - ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
掲載ID:
openreview:5crqglopnf - Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
掲載ID:
openreview:npvbaoc87e - Emergent Analogical Reasoning in Transformers
掲載ID:
openreview:gxtkgmbiz8 - Evolving Interpretable Constitutions for Multi-Agent Coordination
掲載ID:
openreview:2rukwu6ti3 - Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
掲載ID:
openreview:t67db38qhr - In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
掲載ID:
openreview:bufssoupha - Incorporating Importance Weighting in Optimal Transport Based Domain Alignment
掲載ID:
openreview:r8hbst2j4e - Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO
掲載ID:
openreview:km8yqb7sfn - Inference-time Alignment with Rewards in Besov Spaces: Provable Advantages of Feature Learning and Multi-Step Policy Updates
掲載ID:
openreview:wqjmcmleyd - Last-Iterate Convergence of Regularized Gradient Methods for Stochastic Monotone Variational Inequalities
掲載ID:
openreview:eirv1oeo7f - MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks
掲載ID:
openreview:a5venxsvpw - PINE: Pruning Boosted Tree Ensembles with Conformal In-Distribution Prediction Equivalence
掲載ID:
openreview:lxay8upvuc - Positive-Unlabeled Learning with Extreme Scarcity of Labeled Positives
掲載ID:
openreview:pffrikahiz - Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small Models
掲載ID:
openreview:wyqlim30ln - Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
掲載ID:
openreview:ddowwwinhz - Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning
掲載ID:
openreview:bgm2hmxexq - Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games
掲載ID:
openreview:ssqdicpjv1 - SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora
掲載ID:
openreview:y1czgbuum5 - Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
掲載ID:
openreview:uyizpry7ks - Steering at the Source: Style Modulation Heads for Robust Persona Control
掲載ID:
openreview:r6eukr1hq4 - Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation
掲載ID:
openreview:djnbmwe0ek - Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian Noise
掲載ID:
openreview:wb6hwu2jdb - Zero-Flow Encoders
掲載ID:
openreview:vwqk8kdlhy
2025年
- Corrupted Learning Dynamics in Games
掲載ID:
pmlr:v291:tsuchiya25a - Data-dependent Bounds with $T$-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching
掲載ID:
pmlr:v291:nguyen25a - Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback
掲載ID:
pmlr:v291:ito25a - The Adaptive Complexity of Finding a Stationary Point
掲載ID:
pmlr:v291:huanjian25a - $q$-exponential family for policy optimization
掲載ID:
iclr:2025:6507b115562bb0a305f1958ccc87355a - CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
掲載ID:
iclr:2025:70fa5df8e3300dc30bf19bee44a56155 - Direct Distributional Optimization for Provable Alignment of Diffusion Models
掲載ID:
iclr:2025:b51b50262b492dd89bb9cd3105a46702 - EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos
掲載ID:
iclr:2025:bf78fc727cf882df66e6dbc826161e86 - Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse Policies
掲載ID:
iclr:2025:e51ec47238fc3e82c269965c5533f9ef - Flow matching achieves almost minimax optimal convergence
掲載ID:
iclr:2025:44a427b77e9727fcec560e2f8d6925e0 - HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
掲載ID:
iclr:2025:e32aefe039c94b95505b243e4cff8aa2 - Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear Extension
掲載ID:
iclr:2025:1780db9272f81961459f4906036ebc6f - Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization
掲載ID:
iclr:2025:091166620a04a289c555f411d8899049 - Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
掲載ID:
iclr:2025:46535d91c702f03225fc3490a351abcb - Learning View-invariant World Models for Visual Robotic Manipulation
掲載ID:
iclr:2025:8882d370cdafec9885b918a8cfac642e - MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions
掲載ID:
iclr:2025:794a425a2e47e05d29d30f79b79a692d - Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning
掲載ID:
iclr:2025:6dd91fec726dbed8915a1fbadd91d1d2 - Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment
掲載ID:
iclr:2025:f3024ea88cec9f45a411cf4d51ab649c - Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
掲載ID:
iclr:2025:8f6b47b542c9b00ed629250d070dd942 - On the Optimal Memorization Capacity of Transformers
掲載ID:
iclr:2025:a6fb8b1284a412543d853bfdddfc8f8e - On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
掲載ID:
iclr:2025:a1e0d6fa0c30b7d4f75dd9c7ed6189f2 - Open-Set Graph Anomaly Detection via Normal Structure Regularisation
掲載ID:
iclr:2025:2d0842550e6d92b0e27e7e810b1a4792 - Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
掲載ID:
iclr:2025:ead8e195df586b9e7c10fcd114a6b9d1 - Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based Sampling
掲載ID:
iclr:2025:448fc91f669c15d10364ee01d512cc10 - Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image Denoising
掲載ID:
iclr:2025:808a79d149c9dd8338d789881c9dab4c - Realistic Evaluation of Deep Partial-Label Learning Algorithms
掲載ID:
iclr:2025:d5b7afe24b3b891138105a5877b7decd - Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
掲載ID:
iclr:2025:380a0b16a7e6f8c5010f798c9f2d3c61 - Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
掲載ID:
iclr:2025:6faf3b8ed0df532c14d0fc009e451b6d - Revolutionizing EMCCD Denoising through a Novel Physics-Based Learning Framework for Noise Modeling
掲載ID:
iclr:2025:0cd1eec0eeaf5ce1bf6d8875a7c1d095 - Sharpness-Aware Black-Box Optimization
掲載ID:
iclr:2025:9684f0d2b140d1632deef5da23d84f31 - SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training
掲載ID:
iclr:2025:57faf5642eb06e0602b95f6aa989b38a - State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
掲載ID:
iclr:2025:b4f6c4a82ff58ff125b13adf816956a7 - Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling
掲載ID:
iclr:2025:06e2dd57e90a736a5a1fd3bb2bf95c6c - T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning
掲載ID:
iclr:2025:746d2254f6892f3badadb07cc9c0f0da - TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
掲載ID:
iclr:2025:81a0a519bf7ef7757ff46df2065e7051 - Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
掲載ID:
iclr:2025:3a91841d2bcc0b13a3d0d5d60c9f0581 - Towards Neural Scaling Laws for Time Series Foundation Models
掲載ID:
iclr:2025:d04e47d0fdca09e898885c66b67b1e95 - Towards Out-of-Modal Generalization without Instance-level Modal Correspondence
掲載ID:
iclr:2025:437cd2749391ad40f67e4dd1d87c4596 - Transformers Provably Solve Parity Efficiently with Chain of Thought
掲載ID:
iclr:2025:6e2986deda273d8fb903342841fcc4dc - UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
掲載ID:
iclr:2025:c4800e97411c7f199b2895425f2933a5 - Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
掲載ID:
iclr:2025:514b48017505dc778c6db2d845cbbe24 - Adaptive Localization of Knowledge Negation for Continual LLM Unlearning
掲載ID:
pmlr:v267:wuerkaixi25a - BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
掲載ID:
pmlr:v267:li25ah - Benign Overfitting in Token Selection of Attention Mechanism
掲載ID:
pmlr:v267:sakamoto25a - Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
掲載ID:
pmlr:v267:minegishi25a - Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
掲載ID:
pmlr:v267:higuchi25a - Distillation of Discrete Diffusion through Dimensional Correlations
掲載ID:
pmlr:v267:hayakawa25a - Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method
掲載ID:
pmlr:v267:han25f - Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance
掲載ID:
pmlr:v267:wang25cv - Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
掲載ID:
pmlr:v267:omura25a - Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering
掲載ID:
pmlr:v267:yang25o - Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
掲載ID:
pmlr:v267:kim25aj - Mind the Gap: A Practical Attack on GGUF Quantization
掲載ID:
pmlr:v267:egashira25a - Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
掲載ID:
pmlr:v267:kawata25a - Modified K-means Algorithm with Local Optimality Guarantees
掲載ID:
pmlr:v267:li25bt - Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
掲載ID:
pmlr:v267:zhang25di - Nonlinear transformers can perform inference-time feature learning
掲載ID:
pmlr:v267:nishikawa25a - On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
掲載ID:
pmlr:v267:xu25x - On the Role of Label Noise in the Feature Learning Process
掲載ID:
pmlr:v267:han25c - Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models
掲載ID:
pmlr:v267:zhou25x - Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
掲載ID:
pmlr:v267:nitanda25a - Provable In-Context Vector Arithmetic via Retrieving Task Concepts
掲載ID:
pmlr:v267:bu25a - Quantifying Memory Utilization with Effective State-Size
掲載ID:
pmlr:v267:parnichkun25a - SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics
掲載ID:
pmlr:v267:zhu25af - WILTing Trees: Interpreting the Distance Between MPNN Embeddings
掲載ID:
pmlr:v267:negishi25a - You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption
掲載ID:
pmlr:v267:ran25a - A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
掲載ID:
neurips:2025:3ff71ee3d8ec70e172be0b2d56e73481 - A Temporal Difference Method for Stochastic Continuous Dynamics
掲載ID:
neurips:2025:24534dae72f0c92defec92aa50aa9836 - AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
掲載ID:
neurips:2025:328b81881da145412f2bc56c998dfb6a - Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
掲載ID:
neurips:2025:0a50497b94c379b16dfb9b0c959a708e - Bandit and Delayed Feedback in Online Structured Prediction
掲載ID:
neurips:2025:2567c95fd41459a98a73ba893775d22a - Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks
掲載ID:
neurips:2025:5f63999aa6b4011a3615c2508c622821 - Continuous Domain Generalization
掲載ID:
neurips:2025:35c1d69d23bb5dd6b9abcd68be005d5c - Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
掲載ID:
neurips:2025:c98ef086dc70d528e1c1aa1e66893365 - DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
掲載ID:
neurips:2025:02dd0db10c40092de3d9ec2508d12f60 - Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task Conditioning
掲載ID:
neurips:2025:20eadb6338a53114a6371f102c5ded95 - DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
掲載ID:
neurips:2025:bbba680acd2826f23928c6675a19f0e7 - EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
掲載ID:
neurips:2025:3e9412a9c1d93810ef3ef7825115016b - From Self-Check to Consensus: Bayesian Strategic Decoding in Large Language Models
掲載ID:
neurips:2025:492a505f15cd36ec31183df4b8f5aebc - From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
掲載ID:
neurips:2025:6499b639e8a4b5c9a780d9b88c09722f - Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
掲載ID:
neurips:2025:0d3496dd0cec77a999c98d35003203ca - Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
掲載ID:
neurips:2025:6452dcae2bc15073c225fc484cff6988 - GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
掲載ID:
neurips:2025:9ca825deb6ce588c96f880728d3b8aea - Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
掲載ID:
neurips:2025:3dca8a6a5422c2d5d22c6e9a26469d7e - How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning
掲載ID:
neurips:2025:d7b351608d824a4680344a02b180a947 - How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
掲載ID:
neurips:2025:ffab50f3cad7cb5733ca324e5be20976 - I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
掲載ID:
neurips:2025:77fa0e7d45c6687f1958de0b31e9fc05 - Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
掲載ID:
neurips:2025:13b501c58ae3bfe9635a259f4414e943 - Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
掲載ID:
neurips:2025:33201f38001dd381aba2c462051449ba - Learning Simple Interpolants for Linear Integer Arithmetic
掲載ID:
neurips:2025:58acaf7b9aecc9604c7a6aac2eb81035 - Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
掲載ID:
neurips:2025:7af69384b59897a2377a0d46d67a5de2 - Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
掲載ID:
neurips:2025:25c592c5ae46736181075d3f3730709e - Optimal Regret of Bandits under Differential Privacy
掲載ID:
neurips:2025:a70522d112322111cbf19c69e927eaf2 - Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model
掲載ID:
neurips:2025:a821bd31e93435b50c0a461337fe75c0 - Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
掲載ID:
neurips:2025:435e8fbbfc2c6072d4f3a5cb6e56a39a - Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization
掲載ID:
neurips:2025:df2034a516cbd617a96492cc476276c9 - Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians
掲載ID:
neurips:2025:cca569b38ec3612904e625dad7a743dc - Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
掲載ID:
neurips:2025:78847077020397ffff2479316c318073 - Self Iterative Label Refinement via Robust Unlabeled Learning
掲載ID:
neurips:2025:2d3569e4d2ca7e8edeed31a09f817bd9 - Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis
掲載ID:
neurips:2025:6ee0ebd0983f0926496b7d4e0d48b8e3 - Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention
掲載ID:
neurips:2025:220d26c7fb478c2a397bd3fef0fe1d6f - State Size Independent Statistical Error Bound for Discrete Diffusion Models
掲載ID:
neurips:2025:caabce23491e5418f4c9ea348359fcd2 - Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
掲載ID:
neurips:2025:1b4839ff1f843b6be059bd0e8437e975 - The Adaptive Complexity of Minimizing Relative Fisher Information
掲載ID:
neurips:2025:6f1d43d5a82a37e89b0665b33bf3a182 - The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model
掲載ID:
neurips:2025:18ddfb199d71a8a24f83abc1ced077b7 - Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
掲載ID:
neurips:2025:147521db4d049c75cf18d9ff96bf68f5 - Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
掲載ID:
neurips:2025:0f9e0309d8a947ca44463a9b7e8b6a3f - Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
掲載ID:
neurips:2025:3fb6c52aeb11e09053c16eabee74dd7b
2024年
- Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
掲載ID:
pmlr:v247:ito24a - Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
掲載ID:
pmlr:v247:lee24a - Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
掲載ID:
pmlr:v247:oko24a - Online Structured Prediction with Fenchel–Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
掲載ID:
pmlr:v247:sakaue24a - $t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
掲載ID:
iclr:2024:5526c73e3ff4f2a34009e13d15f52fcb - A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making Tasks
掲載ID:
iclr:2024:b5285c0c90186617cbf51afcab06aedb - A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
掲載ID:
iclr:2024:e91bf7dfba0477554994c6d64833e9d8 - Accurate Forgetting for Heterogeneous Federated Continual Learning
掲載ID:
iclr:2024:dd1810bba6fd3d8b7a6f4aa7c263c591 - Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
掲載ID:
iclr:2024:96ee35c170cb8720033b16259c305da9 - Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
掲載ID:
iclr:2024:83ce241ce40aef32225eb2833ca2363c - Exploring Weight Balancing on Long-Tailed Recognition Problem
掲載ID:
iclr:2024:b2647998bc953781490049fe2ac28bf0 - GPAvatar: Generalizable and Precise Head Avatar from Image(s)
掲載ID:
iclr:2024:89ef9ce35c7833cba14bb2381ead6c54 - Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
掲載ID:
iclr:2024:c9e6ac15e689e06139d7b39e1667b165 - Koopman-based generalization bound: New aspect for full-rank weights
掲載ID:
iclr:2024:520fa95508d43d4c5bdfc966c05aff45 - Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
掲載ID:
iclr:2024:5df4313ecd4875931fbdacc486cc1fcf - Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods
掲載ID:
iclr:2024:4e11ee35e17c9807b1a9616b717e548e - Multimodal Web Navigation with Instruction-Finetuned Foundation Models
掲載ID:
iclr:2024:7ef7d8359036afd8c2378d82c21058a4 - Neural Field Classifiers via Target Encoding and Classification Loss
掲載ID:
iclr:2024:ccdfe117c6729267c1595cdf0a587da8 - Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
掲載ID:
iclr:2024:65f54fdf62cd5614dc5715ae7ece4ef6 - Robust Similarity Learning with Difference Alignment Regularization
掲載ID:
iclr:2024:d7ed243b13831bdd468f35039936bcef - SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
掲載ID:
iclr:2024:28ae97a94edbb826ef4a53b5d2df54a3 - Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
掲載ID:
iclr:2024:f2b1b2e974fa5ea622dd87f22815f423 - Theoretical Understanding of Learning from Adversarial Perturbations
掲載ID:
iclr:2024:f9f2deee6f932fdd2041a23f3871e1f1 - Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
掲載ID:
iclr:2024:6d892051f91812700f427250e95e04f5 - Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
掲載ID:
iclr:2024:9e79aefb538d02a7c0610fa43bdb0d0f - Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
掲載ID:
iclr:2024:2c37c5bcef24b9541550261dcd63261b - VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
掲載ID:
iclr:2024:916cb4e1aeafaa0757953c9bacd17337 - Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data
掲載ID:
iclr:2024:c226d7bd4d9a3542a95c6a738e18463b - Vision-Language Foundation Models as Effective Robot Imitators
掲載ID:
iclr:2024:71639c317fb0bf398835627b4418693e - When Semantic Segmentation Meets Frequency Aliasing
掲載ID:
iclr:2024:bcade016e3004543b289b33e7deb7472 - A General Framework for Learning from Weak Supervision
掲載ID:
pmlr:v235:chen24ar - A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
掲載ID:
pmlr:v235:lee24c - Balancing Similarity and Complementarity for Federated Learning
掲載ID:
pmlr:v235:yan24a - Bottleneck-Minimal Indexing for Generative Document Retrieval
掲載ID:
pmlr:v235:du24j - Community-Invariant Graph Contrastive Learning
掲載ID:
pmlr:v235:tan24b - Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
掲載ID:
pmlr:v235:xie24i - Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning
掲載ID:
pmlr:v235:osa24a - Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation
掲載ID:
pmlr:v235:qian24c - Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
掲載ID:
pmlr:v235:tsuchiya24a - Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
掲載ID:
pmlr:v235:zhang24t - High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
掲載ID:
pmlr:v235:chen24aa - How do Transformers Perform In-Context Autoregressive Learning ?
掲載ID:
pmlr:v235:sander24a - Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
掲載ID:
pmlr:v235:wang24ac - Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
掲載ID:
pmlr:v235:fan24c - Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning
掲載ID:
pmlr:v235:yamamoto24a - Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
掲載ID:
pmlr:v235:takakura24a - Mechanistic Design and Scaling of Hybrid Architectures
掲載ID:
pmlr:v235:poli24a - NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
掲載ID:
pmlr:v235:ju24b - Position: Relational Deep Learning - Graph Representation Learning on Relational Databases
掲載ID:
pmlr:v235:fey24a - Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
掲載ID:
pmlr:v235:bu24a - Rethinking Momentum Knowledge Distillation in Online Continual Learning
掲載ID:
pmlr:v235:michel24a - SILVER: Single-loop variance reduction and application to federated learning
掲載ID:
pmlr:v235:oko24a - State-Free Inference of State-Space Models: The *Transfer Function* Approach
掲載ID:
pmlr:v235:parnichkun24a - Symmetry Induces Structure and Constraint of Learning
掲載ID:
pmlr:v235:ziyin24a - Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
掲載ID:
pmlr:v235:kim24af - Understanding Diffusion Models by Feynman’s Path Integral
掲載ID:
pmlr:v235:hirono24a - Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
掲載ID:
pmlr:v235:liu24bh - A Framework for Bilevel Optimization on Riemannian Manifolds
掲載ID:
neurips:2024:bc1c5e5fb8ed1ef9b9b5abced2022e40 - A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
掲載ID:
neurips:2024:0fd489e5e393f61b355be86ed4c24a54 - A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
掲載ID:
neurips:2024:9adc8ada9183f4b9a007a02773fd8114 - ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
掲載ID:
neurips:2024:84d286e32bbee8fa3a86ee9c50e00081 - CV-VAE: A Compatible Video VAE for Latent Generative Video Models
掲載ID:
neurips:2024:1787533e171dcc8549cc2eb5a4840eec - Continuous Temporal Domain Generalization
掲載ID:
neurips:2024:e6f32e64b9c27d153b46c94f0fe22b56 - Controlling Continuous Relaxation for Combinatorial Optimization
掲載ID:
neurips:2024:54191f424e9013fc1d7b923f6e45dff4 - Dealing with Synthetic Data Contamination in Online Continual Learning
掲載ID:
neurips:2024:5bed8703db85ab27dc32f6a42f8fbdb6 - Deep Homomorphism Networks
掲載ID:
neurips:2024:65f54fdf62cd5614dc5715ae7ece4ef6 - Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
掲載ID:
neurips:2024:84409c45a0defe347c895b004b1c675b - Exploiting LLM Quantization
掲載ID:
neurips:2024:496720b3c860111b95ac8634349dcc88 - Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
掲載ID:
neurips:2024:b84cbefc3bebbb88811e2ead03c9ef0c - Generalizable and Animatable Gaussian Head Avatar
掲載ID:
neurips:2024:6a14c7f9fb3f42645cfa6bd5aa446819 - Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming
掲載ID:
neurips:2024:1780db9272f81961459f4906036ebc6f - Geometric-Averaged Preference Optimization for Soft Preference Labels
掲載ID:
neurips:2024:688c7a82e31653e7c256c6c29fd3b438 - Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
掲載ID:
neurips:2024:6de71272e0be559af3f76b884e94794b - In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
掲載ID:
neurips:2024:510d0935b543a29d686f93fa52d1c288 - Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion
掲載ID:
neurips:2024:84f44b36ceb4fbc9bb269959f4796eed - LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image
掲載ID:
neurips:2024:084727e8abf90a8365b940036329cb6f - Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
掲載ID:
neurips:2024:e142fd2b70f10db2543c64bca1417de8 - Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
掲載ID:
neurips:2024:6bd5fca2074dcd9ede9de50f71f7ec28 - No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
掲載ID:
neurips:2024:698cfaf72a208aef2e78bcac55b74328 - Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
掲載ID:
neurips:2024:78ed45281dd746a265fff16ff75a02e5 - On the Comparison between Multi-modal and Single-modal Contrastive Learning
掲載ID:
neurips:2024:94840c41497ead6a84f493f029eba7fa - On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
掲載ID:
neurips:2024:7169e48889a07662f4168e3911c4a69e - Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
掲載ID:
neurips:2024:aa933b5abc1be30baece1d230ec575a7 - Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting
掲載ID:
neurips:2024:7b122d0a0dcb1a86ffa25ccba154652b - Persistent Test-time Adaptation in Recurring Testing Scenarios
掲載ID:
neurips:2024:df29d63af05cb91d705cf06ba5945b9d - Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
掲載ID:
neurips:2024:8d6c356c82252032a20c749dda36f2d8 - Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
掲載ID:
neurips:2024:6b9320bee0e8dc092e8d780b9afd686f - Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
掲載ID:
neurips:2024:73efab19ebde03ff0958f4f155483f57 - ReVideo: Remake a Video with Motion and Content Control
掲載ID:
neurips:2024:20e6b4dd2b1f82bc599c593882f67f75 - Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
掲載ID:
neurips:2024:0f5cb62a8e3331b253c232e229cd551e - Risk-sensitive control as inference with Rényi divergence
掲載ID:
neurips:2024:836cf992a71f7a0bda218c180f942902 - SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
掲載ID:
neurips:2024:d63cf0622eed012a17fe88fced64dcb8 - Slight Corruption in Pre-training Data Makes Better Diffusion Models
掲載ID:
neurips:2024:e45c8d054739d31676619e7e11327f68 - Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics
掲載ID:
neurips:2024:948b1c9d660d7286dd767cd07dabd487 - Taming the Long Tail in Human Mobility Prediction
掲載ID:
neurips:2024:6294e6ec40d3599dcc9e9d584d959f5c - Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment
掲載ID:
neurips:2024:abe31a12e83111fdf2cfd54deed5a2ce - TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge
掲載ID:
neurips:2024:9b01c4a7d3fc49875dad3c13848bcd9e - Transformers are Minimax Optimal Nonparametric In-Context Learners
掲載ID:
neurips:2024:c11daad0a48ea5f3c5c6390c7b060720 - Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
掲載ID:
neurips:2024:fcc22e5b7d5d2155d994da22d045f0a6 - Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
掲載ID:
neurips:2024:14da7aea05debb963b3d8d46449d51a0 - Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
掲載ID:
neurips:2024:f49287371916715b9209fa41a275851e - What Makes Partial-Label Learning Algorithms Effective?
掲載ID:
neurips:2024:a2f1a33355610e271b8a27f09dac83d2 - Wide Two-Layer Networks can Learn from Adversarial Perturbations
掲載ID:
neurips:2024:6e0274fdb05f21654421db43cd8de042
2023年
- 3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation
掲載ID:
openreview:4dzebj83oxk - A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
掲載ID:
openreview:hcuf-qwzefh - A View From Somewhere: Human-Centric Face Representations
掲載ID:
openreview:mmainr0r0c - Collaborative Pure Exploration in Kernel Bandit
掲載ID:
openreview:hlbej6jobdd - Dataset Pruning: Reducing Training Data by Examining Generalization Influence
掲載ID:
openreview:4wziaxd29tq - DiffusER: Diffusion via Edit-based Reconstruction
掲載ID:
openreview:ng9rf9z1yy3 - Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods
掲載ID:
openreview:6doxhqwmayf - Interaction-Based Disentanglement of Entities for Object-Centric World Models
掲載ID:
openreview:jqc2vowqczz - Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
掲載ID:
openreview:fzdjqgy05rz - Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
掲載ID:
openreview:d3qnwd_pcfv - On the Word Boundaries of Emergent Languages Based on Harris's Articulation Scheme
掲載ID:
openreview:b4t9_xast6g - Quantized Compressed Sensing with Score-Based Generative Models
掲載ID:
openreview:oowlrfai_v_ - Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning
掲載ID:
openreview:3ulaihxn9u7 - Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics
掲載ID:
openreview:_jscuk9tbun - What shapes the loss landscape of self supervised learning?
掲載ID:
openreview:3zsn48ruo8m - A Category-theoretical Meta-analysis of Definitions of Disentanglement
掲載ID:
pmlr:v202:zhang23ak - Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
掲載ID:
pmlr:v202:takakura23a - Beyond In-Domain Scenarios: Robust Density-Aware Calibration
掲載ID:
pmlr:v202:tomani23a - Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
掲載ID:
pmlr:v202:kinoshita23a - DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning
掲載ID:
pmlr:v202:murata23b - Diffusion Models are Minimax Optimal Distribution Estimators
掲載ID:
pmlr:v202:oko23a - Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
掲載ID:
pmlr:v202:dong23d - End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
掲載ID:
pmlr:v202:taniguchi23a - GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
掲載ID:
pmlr:v202:ghamizi23a - Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators
掲載ID:
pmlr:v202:parmas23a - On the Stepwise Nature of Self-Supervised Learning
掲載ID:
pmlr:v202:simon23a - Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
掲載ID:
pmlr:v202:lee23d - Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
掲載ID:
pmlr:v202:nitanda23a - Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation
掲載ID:
pmlr:v202:yamasaki23a - Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
掲載ID:
pmlr:v202:kitamura23a - Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster $\text{L}$-/$\text{L}^\natural$-Convex Function Minimization
掲載ID:
pmlr:v202:sakaue23a - Tight and fast generalization error bound of graph embedding in metric space
掲載ID:
pmlr:v202:suzuki23a - spred: Solving L1 Penalty with SGD
掲載ID:
pmlr:v202:ziyin23a - A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization
掲載ID:
neurips:2023:52da50b1ef221e4b1793e3bf44dd973d - Adapting to Continuous Covariate Shift via Online Density Ratio Estimation
掲載ID:
neurips:2023:5cad96c4433955a2e76749ee74a424f5 - Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds
掲載ID:
neurips:2023:1d49235669869ab737c1da9d64b7c769 - Adversarial Training from Mean Field Perspective
掲載ID:
neurips:2023:edcd1aa172dceda2ea9d45a48f25d3e3 - An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination
掲載ID:
neurips:2023:07a363fd2263091c2063998e0034999c - Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
掲載ID:
neurips:2023:ccf4a7323b9ee3e54bf77f0e876b3f8b - Binary Classification with Confidence Difference
掲載ID:
neurips:2023:12c118ef87fde56a10bd858842781b34 - Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning
掲載ID:
neurips:2023:5195825ee60d7efc1e42b7f3f3137040 - Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction
掲載ID:
neurips:2023:32133a6a24d6554263d3584e3ac10faa - Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image
掲載ID:
neurips:2023:3af8c40dcf1bc94fa570a5e42edf219d - Distributional Pareto-Optimal Multi-Objective Reinforcement Learning
掲載ID:
neurips:2023:32285dd184dbfc33cb2d1f0db53c23c5 - Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
掲載ID:
neurips:2023:46d943bc6a15a57c923829efc0db7c7a - DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views
掲載ID:
neurips:2023:0a003511b09274348b8117f5f3b94c93 - Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
掲載ID:
neurips:2023:ef4f2a0232a246b8a502135175e08953 - Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
掲載ID:
neurips:2023:364071531ff2398e0fb8bae31f615b69 - Fast Partitioned Learned Bloom Filter
掲載ID:
neurips:2023:7b2e844c52349134268e819a9b56b9e8 - Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case
掲載ID:
neurips:2023:d84c0dd9b1bfeee361f3268dcaebf849 - Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
掲載ID:
neurips:2023:6cc321baf0a8611b1d1bdbd18822667b - Foundation Model is Efficient Multimodal Multitask Model Selector
掲載ID:
neurips:2023:687b7b2bdcc2ced577c0a989b44e7078 - Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems
掲載ID:
neurips:2023:4c2092ec0b1370cce3fb5965ab255fae - Gradient-Based Feature Learning under Structured Data
掲載ID:
neurips:2023:e21955c93dede886af1d0d362c756757 - High-dimensional Contextual Bandit Problem without Sparsity
掲載ID:
neurips:2023:9b35a0a20d617dc68ae98a7a57df2f51 - Imitation Learning from Vague Feedback
掲載ID:
neurips:2023:96e35b532b4932a86cce8c929ff3f960 - Improving Language Plasticity via Pretraining with Active Forgetting
掲載ID:
neurips:2023:6450ea28ebbc8437bc38775157818172 - Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
掲載ID:
neurips:2023:371355cd42caaf83412c3fbef4688979 - Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
掲載ID:
neurips:2023:38a1671ab0747b6ffe4d1c6ef117a3a9 - LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning
掲載ID:
neurips:2023:f0606b882692637835e8ac981089eccd - On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
掲載ID:
neurips:2023:040d3b6af368bf71f952c18da5713b48 - Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost
掲載ID:
neurips:2023:5ef04392708bb2340cb9b7da41225660 - Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
掲載ID:
neurips:2023:9408564a4229f4a933ac9bd09a29ee96
2022年
- Dimension-free convergence rates for gradient Langevin dynamics in RKHS
掲載ID:
pmlr:v178:muzellec22a - Convergent and Efficient Deep Q Learning Algorithm
掲載ID:
iclr:2022:486c825db2f776da72d0b7a791f45b8f - Disentanglement Analysis with Partial Information Decomposition
掲載ID:
iclr:2022:eb86d510361fc23b59f18c1bc9802cc6 - Dropout Q-Functions for Doubly Efficient Reinforcement Learning
掲載ID:
iclr:2022:d61e4bbd6393c9111e6526ea173a7c8b - Exploiting Class Activation Value for Partial-Label Learning
掲載ID:
iclr:2022:28e209b61a52482a0ae1cb9f5959c792 - Federated Learning from Only Unlabeled Data with Class-conditional-sharing Clients
掲載ID:
iclr:2022:0533a888904bd4867929dffd884d60b8 - Generalized Decision Transformer for Offline Hindsight Information Matching
掲載ID:
iclr:2022:6d9c547cf146054a5a720606a7694467 - Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness
掲載ID:
iclr:2022:62da8c91ce7b10846231921795d6059e - Learning Causal Models from Conditional Moment Restrictions by Importance Weighting
掲載ID:
iclr:2022:02f039058bd48307e6f653a2005c9dd2 - Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
掲載ID:
iclr:2022:7d6044e95a16761171b130dcb476a43e - Neural Solvers for Fast and Accurate Numerical Optimal Control
掲載ID:
iclr:2022:2e74c2cf88f68a68c84e9509abc7ea56 - Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization
掲載ID:
iclr:2022:1597d21403f63da1bb0539592597a525 - Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
掲載ID:
iclr:2022:ddb30680a691d157187ee1cf9e896d03 - SGD Can Converge to Local Maxima
掲載ID:
iclr:2022:1ff8a7b5dc7a7d1f0ed65aaa29c04b1e - Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
掲載ID:
iclr:2022:d3f5d4de09ea19461dab00590df91e4f - Strength of Minibatch Noise in SGD
掲載ID:
iclr:2022:8710ef761bbb29a6f9d12e4ef8e4379c - Understanding the Variance Collapse of SVGD in High Dimensions
掲載ID:
iclr:2022:c1aeb6517a1c7f33514f7ff69047e74e - Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
掲載ID:
pmlr:v162:xie22d - Adversarial Attack and Defense for Non-Parametric Two-Sample Tests
掲載ID:
pmlr:v162:xu22m - On the Surrogate Gap between Contrastive and Supervised Losses
掲載ID:
pmlr:v162:bao22e - Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding
掲載ID:
pmlr:v162:tsuji22a - Power-Law Escape Rate of SGD
掲載ID:
pmlr:v162:mori22a - Sparse Double Descent: Where Network Pruning Aggravates Overfitting
掲載ID:
pmlr:v162:he22d - To Smooth or Not? When Label Smoothing Meets Noisy Labels
掲載ID:
pmlr:v162:wei22b - A Closer Look at Prototype Classifier for Few-shot Image Classification
掲載ID:
neurips:2022:a559a5a8aa5ae6682ced009ad97cdb16 - Adapting to Online Label Shift with Provable Guarantees
掲載ID:
neurips:2022:c19c4def293b6a63db1ff27143dd4f10 - Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
掲載ID:
neurips:2022:959f70ee50044bed305e48e3484005a7 - Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective
掲載ID:
neurips:2022:c828f33af3c3f669690c2e28ae7af5e2 - Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with Predictions
掲載ID:
neurips:2022:844e61124d9e1f58632bf0c8968ad728 - Efficient Submodular Optimization under Noise: Local Search is Robust
掲載ID:
neurips:2022:a774503daed55eb53c634847ae071ec7 - Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning
掲載ID:
neurips:2022:20bd42d82998bc61732c00452228e814 - Exact Solutions of a Deep Linear Network
掲載ID:
neurips:2022:9a940e858b17f01c402e164835140c4a - FIRE: Semantic Field of Words Represented as Non-Linear Functions
掲載ID:
neurips:2022:f08223bc8d177df6807811c32f5acfed - Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
掲載ID:
neurips:2022:03a90e1bb2ceb2ea165424f2d96aa3a1 - Green Hierarchical Vision Transformer for Masked Image Modeling
掲載ID:
neurips:2022:7e487c72fce6e45879a78ee0872d991d - High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
掲載ID:
neurips:2022:f7e7fabd73b3df96c54a320862afcb78 - Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization
掲載ID:
neurips:2022:78e839f96568985d18463044a064ea0f - Langevin Autoencoders for Learning Deep Latent Variable Models
掲載ID:
neurips:2022:565f995643da6329cec701f26f8579f5 - Large Language Models are Zero-Shot Reasoners
掲載ID:
neurips:2022:8bb0d291acd4acf06ef112099c16f326 - Lazy and Fast Greedy MAP Inference for Determinantal Point Process
掲載ID:
neurips:2022:127179162bfe4c422325ee7d05ad9cd8 - Learning Contrastive Embedding in Low-Dimensional Space
掲載ID:
neurips:2022:297f7c6c56af81239f7c47d21558b75a - Neural Approximation of Graph Topological Features
掲載ID:
neurips:2022:d7ce06e9293c3d8e6cb3f80b4157f875 - Non-rigid Point Cloud Registration with Neural Deformation Pyramid
掲載ID:
neurips:2022:b2077e6d66da612fcb701589efa9ce88 - Posterior Collapse of a Linear Latent Variable Model
掲載ID:
neurips:2022:f419342f8afd483c781f69c2fabfe4f6 - ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
掲載ID:
neurips:2022:66f7a3df255c47b2e72f30b310a7e44a - Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search
掲載ID:
neurips:2022:136b9a13861308c8948cd308ccd02658 - Single Loop Gaussian Homotopy Method for Non-convex Optimization
掲載ID:
neurips:2022:2e622ac74f66df03b686a12e2e0e4424 - Synergy-of-Experts: Collaborate to Improve Adversarial Robustness
掲載ID:
neurips:2022:d16152d53088ad779ffa634e7bf66166 - Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime
掲載ID:
neurips:2022:d2155b1f7eb42350d7bc3013eefe5480 - When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
掲載ID:
neurips:2022:760b5def8dcb1156aac454e9c0f5f406
掲載対象外の論文や未反映の論文は、この一覧には含まれません。