大学 × Machine Learning
京都大学
Machine Learning / 2022–2026 LIVE
掲載論文 63 本
論文一覧
63 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 63 本と一致しています。
2026年
- Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
掲載ID:
pmlr:v336:lee26a - Learning Periodic Strategies in Blocking Bandits Is as Hard as Bandits with Switching Costs
掲載ID:
pmlr:v336:cesa-bianchi26a - DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
掲載ID:
iclr:2026:c056d6cf7b7108418f2b8c307dfaab02 - Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory
掲載ID:
iclr:2026:9f07b279e11b1518136e8fdaa619ea5d - FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
掲載ID:
iclr:2026:427f20d90386fd27804f1831d6a3d48f - MVR: Multi-view Video Reward Shaping for Reinforcement Learning
掲載ID:
iclr:2026:617f72363e338e0a945b8a39df2196cc - OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
掲載ID:
iclr:2026:5c1863f711c721648387ac2ef745facb - On Fairness of Task Arithmetic: The Role of Task Vectors
掲載ID:
iclr:2026:186c95238d737f419846b244e6bd2f28 - Readout Representation: Redefining Neural Codes by Input Recovery
掲載ID:
iclr:2026:5f326d2e040a20d52438873f5d727e58 - Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
掲載ID:
iclr:2026:e36675ab46e276069ec9ea0b61125d0b - Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization
掲載ID:
openreview:rakocnp4uz - Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets
掲載ID:
openreview:iwv5o07bxv - Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
掲載ID:
openreview:npvbaoc87e - Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
掲載ID:
openreview:aih1jyu37z - How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
掲載ID:
openreview:mk3xwe7p2t - SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
掲載ID:
openreview:hxyv6xehko - SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora
掲載ID:
openreview:y1czgbuum5 - Supervised Graph Contrastive Learning for Gene Regulatory Networks
掲載ID:
openreview:0y7itv1kb7
2025年
- GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
掲載ID:
iclr:2025:a924b7178e5975dfed1de235f0b72973 - Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
掲載ID:
iclr:2025:8f6b47b542c9b00ed629250d070dd942 - PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis
掲載ID:
iclr:2025:ab41313eaa3cbedbe491c24cbfe6547d東京科学大学 / 京都大学 / 沖縄科学技術大学院大学
- Scalable Decentralized Learning with Teleportation
掲載ID:
iclr:2025:b3732a13897c4cea145c3bdece80de64 - SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches
掲載ID:
iclr:2025:159511050630689045bf5593e74b13cc - Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
掲載ID:
pmlr:v267:sonoda25a - Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance
掲載ID:
pmlr:v267:chen25bw - Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
掲載ID:
pmlr:v267:takezawa25a - Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems
掲載ID:
pmlr:v267:chen25ai - Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering
掲載ID:
pmlr:v267:yang25o - Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
掲載ID:
pmlr:v267:nakanishi25a - Generative Perception of Shape and Material from Differential Motion
掲載ID:
neurips:2025:b4e49c75933caedcc079b2d6289cb079 - Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
掲載ID:
neurips:2025:617f72363e338e0a945b8a39df2196cc - Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model
掲載ID:
neurips:2025:93da65de953f738e7160ef1125e288d1 - Optimal Estimation of the Best Mean in Multi-Armed Bandits
掲載ID:
neurips:2025:04bb165d5fb90aef582f39a58f4bf072 - Optimal Regret of Bandits under Differential Privacy
掲載ID:
neurips:2025:a70522d112322111cbf19c69e927eaf2 - Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
掲載ID:
neurips:2025:435e8fbbfc2c6072d4f3a5cb6e56a39a - Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
掲載ID:
neurips:2025:78847077020397ffff2479316c318073
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 - Online Structured Prediction with Fenchel–Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
掲載ID:
pmlr:v247:sakaue24a - Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
掲載ID:
iclr:2024:5df4313ecd4875931fbdacc486cc1fcf - End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations
掲載ID:
pmlr:v235:luo24j - Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
掲載ID:
pmlr:v235:tsuchiya24a - Self-attention Networks Localize When QK-eigenspectrum Concentrates
掲載ID:
pmlr:v235:bao24b - AUC Maximization under Positive Distribution Shift
掲載ID:
neurips:2024:3f8c7eb848ffec848f3ed2b7ca44915d - Enhancing Chess Reinforcement Learning with Graph Representation
掲載ID:
neurips:2024:008a16ead32f932b711788c276890456 - Multistable Shape from Shading Emerges from Patch Diffusion
掲載ID:
neurips:2024:3d4dc72d715bd6415d356293079adf3d - Parameter-free Clipped Gradient Descent Meets Polyak
掲載ID:
neurips:2024:4ebba705ffdee81e0a638c99fe066ce2 - Risk-sensitive control as inference with Rényi divergence
掲載ID:
neurips:2024:836cf992a71f7a0bda218c180f942902 - Zipfian Whitening
掲載ID:
neurips:2024:dd1fef536655685898a6602bfbf16857
2023年
- Proper Losses, Moduli of Convexity, and Surrogate Regret Bounds
掲載ID:
pmlr:v195:bao23a - Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure
掲載ID:
pmlr:v202:sato23a - Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators
掲載ID:
pmlr:v202:parmas23a - Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
掲載ID:
pmlr:v202:lee23d - Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence
掲載ID:
neurips:2023:f201b3f3d0f08c6ab46c36b9052c1b64 - Modeling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network
掲載ID:
neurips:2023:4c9477b9e2c7ec0ad3f4f15077aaf85a - Regularizing Neural Networks with Meta-Learning Generative Models
掲載ID:
neurips:2023:572cd21bd5dea96b065476b77d21b3c6 - Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
掲載ID:
neurips:2023:9408564a4229f4a933ac9bd09a29ee96
2022年
- Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
掲載ID:
pmlr:v178:ito22a - Re-evaluating Word Mover’s Distance
掲載ID:
pmlr:v162:sato22b - Learning Deep Input-Output Stable Dynamics
掲載ID:
neurips:2022:364721b3d5d9da2aaa19adafd7b0f49c - Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification
掲載ID:
neurips:2022:43c18853329c7504996b255252b6cb1f - Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
掲載ID:
neurips:2022:b7aea253ab34a773967f1e4cdea9e4fb - Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms
掲載ID:
neurips:2022:bbc9d480a8257889d2af88983e8b126a
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。