Conferences · eligible papers
COLT
2021–2025 確定版
2021 · 140 papers
このEditionに反映済みのmain full research papersのみ掲載しています。著者リンクは日本の大学への著者別所属根拠がある場合に限ります。
- (Nearly) Dimension Independent Private ERM with AdaGrad Rates\{via Publicly Estimated Subspaces
日本大学: 関与なし(対象大学)
- **Paper retracted by author request (see pdf for retraction notice from the authors)** Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping
日本大学: 関与なし(対象大学)
- A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation
日本大学: 関与なし(対象大学)
- A Law of Robustness for Two-Layers Neural Networks
日本大学: 関与なし(対象大学)
- A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network
日本大学: 関与なし(対象大学)
- A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Partial Differential Equations
日本大学: 関与なし(対象大学)
- A Statistical Taylor Theorem and Extrapolation of Truncated Densities
日本大学: 関与なし(対象大学)
- A Theory of Heuristic Learnability
日本大学: 関与なし(対象大学)
- Adaptive Discretization for Adversarial Lipschitz Bandits
日本大学: 関与なし(対象大学)
- Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium
日本大学: 関与なし(対象大学)
- Adaptivity in Adaptive Submodularity
日本大学: 関与なし(対象大学)
- Adversarially Robust Learning with Unknown Perturbation Sets
日本大学: 関与なし(対象大学)
- Adversarially Robust Low Dimensional Representations
日本大学: 関与なし(対象大学)
- Agnostic Proper Learning of Halfspaces under Gaussian Marginals
日本大学: 関与なし(対象大学)
- Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball
日本大学: 関与なし(対象大学)
- Approximation Algorithms for Socially Fair Clustering
日本大学: 関与なし(対象大学)
- Asymptotically Optimal Information-Directed Sampling
日本大学: 関与なし(対象大学)
- Average-Case Communication Complexity of Statistical Problems
日本大学: 関与なし(対象大学)
- Benign Overfitting of Constant-Stepsize SGD for Linear Regression
日本大学: 関与なし(対象大学)
- Black-Box Control for Linear Dynamical Systems
日本大学: 関与なし(対象大学)
- Boosting in the Presence of Massart Noise
日本大学: 関与なし(対象大学)
- Bounded Memory Active Learning through Enriched Queries
日本大学: 関与なし(対象大学)
- Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints
日本大学: 関与なし(対象大学)
- Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
日本大学: 関与なし(対象大学)
- Concentration of Non-Isotropic Random Tensors with Applications to Learning and Empirical Risk Minimization
日本大学: 関与なし(対象大学)
- Convergence rates and approximation results for SGD and its continuous-time counterpart
日本大学: 関与なし(対象大学)
- Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions
日本大学: 関与なし(対象大学)
- Corruption-robust exploration in episodic reinforcement learning
日本大学: 関与なし(対象大学)
- Deterministic Finite-Memory Bias Estimation
日本大学: 関与なし(対象大学)
- Differentially Private Nonparametric Regression Under a Growth Condition
日本大学: 関与なし(対象大学)
- Double Explore-then-Commit: Asymptotic Optimality and Beyond
日本大学: 関与なし(対象大学)
- Efficient Algorithms for Learning from Coarse Labels
日本大学: 関与なし(対象大学)
- Efficient Bandit Convex Optimization: Beyond Linear Losses
日本大学: 関与なし(対象大学)
- Exact Recovery of Clusters in Finite Metric Spaces Using Oracle Queries
日本大学: 関与なし(対象大学)
- Exponential Weights Algorithms for Selective Learning
日本大学: 関与なし(対象大学)
- Exponential savings in agnostic active learning through abstention
日本大学: 関与なし(対象大学)
- Exponentially Improved Dimensionality Reduction for l1: Subspace Embeddings and Independence Testing
日本大学: 関与なし(対象大学)
- Fast Rates for Structured Prediction
日本大学: 関与なし(対象大学)
- Fast Rates for the Regret of Offline Reinforcement Learning
日本大学: 関与なし(対象大学)
- Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
日本大学: 関与なし(対象大学)
- Frank-Wolfe with a Nearest Extreme Point Oracle
日本大学: 関与なし(対象大学)
- From Local Pseudorandom Generators to Hardness of Learning
日本大学: 関与なし(対象大学)
- Functions with average smoothness: structure, algorithms, and learning
日本大学: 関与なし(対象大学)
- Generalizing Complex Hypotheses on Product Distributions: Auctions, Prophet Inequalities, and Pandora’s Problem
日本大学: 関与なし(対象大学)
- Group testing and local search: is there a computational-statistical gap?
日本大学: 関与なし(対象大学)
- Hypothesis testing with low-degree polynomials in the Morris class of exponential families
日本大学: 関与なし(対象大学)
- Implicit Regularization in ReLU Networks with the Square Loss
日本大学: 関与なし(対象大学)
- Impossibility of Partial Recovery in the Graph Alignment Problem
日本大学: 関与なし(対象大学)
- Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications
日本大学: 関与なし(対象大学)
- Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov Noise
日本大学: 関与なし(対象大学)
- Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions
日本大学: 関与なし(対象大学)
- Improved Regret for Zeroth-Order Stochastic Convex Bandits
日本大学: 関与なし(対象大学)
- Information-Theoretic Generalization Bounds for Stochastic Gradient Descent
日本大学: 関与なし(対象大学)
- Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
日本大学: 関与なし(対象大学)
- Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon
日本大学: 関与なし(対象大学)
- It was “all” for “nothing”: sharp phase transitions for noiseless discrete channels
日本大学: 関与なし(対象大学)
- Johnson-Lindenstrauss Transforms with Best Confidence
日本大学: 関与なし(対象大学)
- Kernel Thinning
日本大学: 関与なし(対象大学)
- Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games
日本大学: 関与なし(対象大学)
- Lazy OCO: Online Convex Optimization on a Switching Budget
日本大学: 関与なし(対象大学)
- Learning and testing junta distributions with sub cube conditioning
日本大学: 関与なし(対象大学)
- Learning from Censored and Dependent Data: The case of Linear Dynamics
日本大学: 関与なし(対象大学)
- Learning in Matrix Games can be Arbitrarily Complex
日本大学: 関与なし(対象大学)
- Learning sparse mixtures of permutations from noisy information
日本大学: 関与なし(対象大学)
- Learning to Sample from Censored Markov Random Fields
日本大学: 関与なし(対象大学)
- Learning to Stop with Surprisingly Few Samples
日本大学: 関与なし(対象大学)
- Learning with invariances in random features and kernel models
日本大学: 関与なし(対象大学)
- Machine Unlearning via Algorithmic Stability
日本大学: 関与なし(対象大学)
- Majorizing Measures, Sequential Complexities, and Online Learning
日本大学: 関与なし(対象大学)
- Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition
日本大学: 関与なし(対象大学)
- Mirror Descent and the Information Ratio
日本大学: 関与なし(対象大学)
- Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
日本大学: 関与なし(対象大学)
- Moment Multicalibration for Uncertainty Estimation
日本大学: 関与なし(対象大学)
- Multiplayer Bandit Learning, from Competition to Cooperation
日本大学: 関与なし(対象大学)
- Near Optimal Distributed Learning of Halfspaces with Two Parties
日本大学: 関与なし(対象大学)
- Near-Optimal Entrywise Sampling of Numerically Sparse Matrices
日本大学: 関与なし(対象大学)
- Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
日本大学: 関与なし(対象大学)
- Non-Euclidean Differentially Private Stochastic Convex Optimization
日本大学: 関与なし(対象大学)
- Non-asymptotic approximations of neural networks by Gaussian processes
日本大学: 関与なし(対象大学)
- Non-stationary Reinforcement Learning without Prior Knowledge: an Optimal Black-box Approach
日本大学: 関与なし(対象大学)
- On Avoiding the Union Bound When Answering Multiple Differentially Private Queries
日本大学: 関与なし(対象大学)
- On Empirical Bayes Variational Autoencoder: An Excess Risk Bound
日本大学: 関与なし(対象大学)
- On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function
日本大学: 関与なし(対象大学)
- On the Approximation Power of Two-Layer Networks of Random ReLUs
日本大学: 関与なし(対象大学)
- On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
日本大学: 関与なし(対象大学)
- On the Minimal Error of Empirical Risk Minimization
日本大学: 関与なし(対象大学)
- On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning
日本大学: 関与なし(対象大学)
- Online Learning from Optimal Actions
日本大学: 関与なし(対象大学)
- Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games
日本大学: 関与なし(対象大学)
- Online Markov Decision Processes with Aggregate Bandit Feedback
日本大学: 関与なし(対象大学)
- Open Problem: Are all VC-classes CPAC learnable?
日本大学: 関与なし(対象大学)
- Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?
日本大学: 関与なし(対象大学)
- Open Problem: Is There an Online Learning Algorithm That Learns Whenever Online Learning Is Possible?
日本大学: 関与なし(対象大学)
- Open Problem: Tight Online Confidence Intervals for RKHS Elements
日本大学: 関与なし(対象大学)
- Optimal Dynamic Regret in Exp-Concave Online Learning
日本大学: 関与なし(対象大学)
- Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm
日本大学: 関与なし(対象大学)
- Optimizing Optimizers: Regret-optimal gradient descent algorithms
日本大学: 関与なし(対象大学)
- Outlier-Robust Learning of Ising Models Under Dobrushin’s Condition
日本大学: 関与なし(対象大学)
- PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
日本大学: 関与なし(対象大学)
- Parameter-Free Multi-Armed Bandit Algorithms with Hybrid Data-Dependent Regret Bounds
日本大学: 関与なし(対象大学)