![[Conference on Learning Theory Logo]](/v134/assets/images/logo-pmlr.svg){kind=logo}
[edit]
Volume 134: Conference on Learning Theory, 15-19 August 2021, Boulder, Colorado, USA
[edit]
Editors: Mikhail Belkin, Samory Kpotufe
Conference on Learning Theory 2021: Post-conference Preface
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:i-iii
[abs][Download PDF]
Stochastic block model entropy and broadcasting on trees with survey
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1-25
[abs][Download PDF]
Regret Minimization in Heavy-Tailed Bandits
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:26-62
[abs][Download PDF]
SGD Generalizes Better Than GD (And Regularization Doesn’t Help)
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:63-92
[abs][Download PDF]
The Bethe and Sinkhorn Permanents of Low Rank Matrices and Implications for Profile Maximum Likelihood
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:93-158
[abs][Download PDF]
Learning in Matrix Games can be Arbitrarily Complex
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:159-185
[abs][Download PDF]
Functions with average smoothness: structure, algorithms, and learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:186-236
[abs][Download PDF]
Adversarially Robust Low Dimensional Representations
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:237-325
[abs][Download PDF]
The Last-Iterate Convergence Rate of Optimistic Mirror Descent in Stochastic Variational Inequalities
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:326-358
[abs][Download PDF]
Optimal Dynamic Regret in Exp-Concave Online Learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:359-409
[abs][Download PDF]
Spectral Planting and the Hardness of Refuting Cuts, Colorability, and Communities in Random Graphs
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:410-473
[abs][Download PDF]
Non-Euclidean Differentially Private Stochastic Convex Optimization
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:474-499
[abs][Download PDF]
Reconstructing weighted voting schemes from partial information about their power indices
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:500-565
[abs][Download PDF]
Deterministic Finite-Memory Bias Estimation
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:566-585
[abs][Download PDF]
Online Learning from Optimal Actions
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:586-586
[abs][Download PDF]
Majorizing Measures, Sequential Complexities, and Online Learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:587-590
[abs][Download PDF]
Robust learning under clean-label attack
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:591-634
[abs][Download PDF]
Rank-one matrix estimation: analytic time evolution of gradient descent dynamics
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:635-678
Multiplayer Bandit Learning, from Competition to Cooperation
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:679-723
[abs][Download PDF]
Near Optimal Distributed Learning of Halfspaces with Two Parties
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:724-758
[abs][Download PDF]
Near-Optimal Entrywise Sampling of Numerically Sparse Matrices
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:759-773
[abs][Download PDF]
Statistical Query Algorithms and Low Degree Tests Are Almost Equivalent
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:774-774
[abs][Download PDF]
Exact Recovery of Clusters in Finite Metric Spaces Using Oracle Queries
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:775-803
[abs][Download PDF]
A Law of Robustness for Two-Layers Neural Networks
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:804-820
[abs][Download PDF]
Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:821-822
[abs][Download PDF]
Fast Rates for Structured Prediction
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:823-865
[abs][Download PDF]
Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:866-882
Optimizing Optimizers: Regret-optimal gradient descent algorithms
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:883-926
[abs][Download PDF]
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:927-1027
[abs][Download PDF]
Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1028-1059
[abs][Download PDF]
Learning and testing junta distributions with sub cube conditioning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1060-1113
[abs][Download PDF]
Black-Box Control for Linear Dynamical Systems
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1114-1143
[abs][Download PDF]
Query complexity of least absolute deviation regression via robust uniform convergence
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1144-1179
[abs][Download PDF]
Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1180-1215
[abs][Download PDF]
Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1216-1259
[abs][Download PDF]
Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1260-1300
[abs][Download PDF]
Online Markov Decision Processes with Aggregate Bandit Feedback
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1301-1329
[abs][Download PDF]
Quantifying Variational Approximation for Log-Partition Function
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1330-1357
[abs][Download PDF]
From Local Pseudorandom Generators to Hardness of Learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1358-1394
[abs][Download PDF]
A Statistical Taylor Theorem and Extrapolation of Truncated Densities
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1395-1398
[abs][Download PDF]
Weak learning convex sets under normal distributions
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1399-1428
[abs][Download PDF]
Learning sparse mixtures of permutations from noisy information
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1429-1466
[abs][Download PDF]
Sparse sketches with small inversion bias
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1467-1510
[abs][Download PDF]
The Sample Complexity of Robust Covariance Testing
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1511-1521
[abs][Download PDF]
Agnostic Proper Learning of Halfspaces under Gaussian Marginals
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1522-1551
[abs][Download PDF]
The Optimality of Polynomial Regression for Agnostic Learning under Gaussian Marginals in the SQ Model
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1552-1584
[abs][Download PDF]
Boosting in the Presence of Massart Noise
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1585-1644
[abs][Download PDF]
Outlier-Robust Learning of Ising Models Under Dobrushin’s Condition
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1645-1682
[abs][Download PDF]
Random Coordinate Langevin Monte Carlo
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1683-1710
[abs][Download PDF]
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1711-1752
[abs][Download PDF]
Kernel Thinning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1753-1753
[abs][Download PDF]
Non-asymptotic approximations of neural networks by Gaussian processes
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1754-1775
[abs][Download PDF]
On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1776-1822
[abs][Download PDF]
Adaptivity in Adaptive Submodularity
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1823-1846
[abs][Download PDF]
Concentration of Non-Isotropic Random Tensors with Applications to Learning and Empirical Risk Minimization
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1847-1886
[abs][Download PDF]
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1887-1936
[abs][Download PDF]
Sequential prediction under log-loss and misspecification
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1937-1964
[abs][Download PDF]
Convergence rates and approximation results for SGD and its continuous-time counterpart
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:1965-2058
[abs][Download PDF]
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2059-2059
[abs][Download PDF]
Efficient Algorithms for Learning from Coarse Labels
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2060-2079
[abs][Download PDF]
Impossibility of Partial Recovery in the Graph Alignment Problem
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2080-2102
[abs][Download PDF]
Frank-Wolfe with a Nearest Extreme Point Oracle
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2103-2132
[abs][Download PDF]
On Avoiding the Union Bound When Answering Multiple Differentially Private Queries
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2133-2146
[abs][Download PDF]
Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2147-2148
[abs][Download PDF]
Differentially Private Nonparametric Regression Under a Growth Condition
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2149-2192
[abs][Download PDF]
Source Identification for Mixtures of Product Distributions
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2193-2216
[abs][Download PDF]
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2217-2247
[abs][Download PDF]
Generalizing Complex Hypotheses on Product Distributions: Auctions, Prophet Inequalities, and Pandora’s Problem
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2248-2288
[abs][Download PDF]
Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2289-2314
[abs][Download PDF]
Shape Matters: Understanding the Implicit Bias of the Noise Covariance
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2315-2357
[abs][Download PDF]
Bounded Memory Active Learning through Enriched Queries
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2358-2387
[abs][Download PDF]
Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2388-2422
[abs][Download PDF]
On the Approximation Power of Two-Layer Networks of Random ReLUs
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2423-2461
[abs][Download PDF]
Fast Rates for the Regret of Offline Reinforcement Learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2462-2462
[abs][Download PDF]
Streaming k-PCA: Efficient guarantees for Oja’s algorithm, beyond rank-one updates
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2463-2498
[abs][Download PDF]
Group testing and local search: is there a computational-statistical gap?
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2499-2551
[abs][Download PDF]
Parameter-Free Multi-Armed Bandit Algorithms with Hybrid Data-Dependent Regret Bounds
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2552-2583
[abs][Download PDF]
Double Explore-then-Commit: Asymptotic Optimality and Beyond
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2584-2633
[abs][Download PDF]
Moment Multicalibration for Uncertainty Estimation
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2634-2678
[abs][Download PDF]
Reduced-Rank Regression with Operator Norm Error
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2679-2716
[abs][Download PDF]
(Nearly) Dimension Independent Private ERM with AdaGrad Rates\{via Publicly Estimated Subspaces
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2717-2746
[abs][Download PDF]
The Sparse Vector Technique, Revisited
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2747-2776
[abs][Download PDF]
Asymptotically Optimal Information-Directed Sampling
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2777-2821
[abs][Download PDF]
Hypothesis testing with low-degree polynomials in the Morris class of exponential families
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2822-2848
[abs][Download PDF]
On the Minimal Error of Empirical Risk Minimization
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2849-2852
[abs][Download PDF]
**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
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2853-2890
[abs][Download PDF]
Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2891-2937
[abs][Download PDF]
Improved Regret for Zeroth-Order Stochastic Convex Bandits
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2938-2964
[abs][Download PDF]
Mirror Descent and the Information Ratio
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2965-2992
[abs][Download PDF]
Structured Logconcave Sampling with a Restricted Gaussian Oracle
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:2993-3050
[abs][Download PDF]
Stochastic Approximation for Online Tensorial Independent Component Analysis
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3051-3106
[abs][Download PDF]
Softmax Policy Gradient Methods Can Take Exponential Time to Converge
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3107-3110
[abs][Download PDF]
Exponentially Improved Dimensionality Reduction for l1: Subspace Embeddings and Independence Testing
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3111-3195
[abs][Download PDF]
A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Partial Differential Equations
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3196-3241
[abs][Download PDF]
Corruption-robust exploration in episodic reinforcement learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3242-3245
[abs][Download PDF]
Approximation Algorithms for Socially Fair Clustering
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3246-3264
[abs][Download PDF]
The Connection Between Approximation, Depth Separation and Learnability in Neural Networks
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3265-3295
[abs][Download PDF]
Random Graph Matching with Improved Noise Robustness
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3296-3329
[abs][Download PDF]
Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3330-3350
[abs][Download PDF]
Learning with invariances in random features and kernel models
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3351-3418
[abs][Download PDF]
Learning to Sample from Censored Markov Random Fields
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3419-3451
[abs][Download PDF]
Adversarially Robust Learning with Unknown Perturbation Sets
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3452-3482
[abs][Download PDF]
A Theory of Heuristic Learnability
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3483-3525
[abs][Download PDF]
Information-Theoretic Generalization Bounds for Stochastic Gradient Descent
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3526-3545
[abs][Download PDF]
It was “all” for “nothing”: sharp phase transitions for noiseless discrete channels
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3546-3547
[abs][Download PDF]
SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3548-3626
[abs][Download PDF]
Provable Memorization via Deep Neural Networks using Sub-linear Parameters
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3627-3661
[abs][Download PDF]
Towards a Query-Optimal and Time-Efficient Algorithm for Clustering with a Faulty Oracle
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3662-3680
[abs][Download PDF]
Towards a Dimension-Free Understanding of Adaptive Linear Control
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3681-3770
[abs][Download PDF]
Learning from Censored and Dependent Data: The case of Linear Dynamics
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3771-3787
Adaptive Discretization for Adversarial Lipschitz Bandits
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3788-3805
[abs][Download PDF]
Exponential savings in agnostic active learning through abstention
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3806-3832
[abs][Download PDF]
Exponential Weights Algorithms for Selective Learning
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3833-3858
[abs][Download PDF]
Average-Case Communication Complexity of Statistical Problems
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3859-3886
[abs][Download PDF]
Learning to Stop with Surprisingly Few Samples
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3887-3888
[abs][Download PDF]
The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3889-3934
[abs][Download PDF]
Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3935-3971
[abs][Download PDF]
Lazy OCO: Online Convex Optimization on a Switching Budget
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3972-3988
[abs][Download PDF]
Johnson-Lindenstrauss Transforms with Best Confidence
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:3989-4007
[abs][Download PDF]
Efficient Bandit Convex Optimization: Beyond Linear Losses
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4008-4067
[abs][Download PDF]
On Empirical Bayes Variational Autoencoder: An Excess Risk Bound
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4068-4125
[abs][Download PDF]
Machine Unlearning via Algorithmic Stability
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4126-4142
A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4143-4173
[abs][Download PDF]
Robust Online Convex Optimization in the Presence of Outliers
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4174-4194
[abs][Download PDF]
Size and Depth Separation in Approximating Benign Functions with Neural Networks
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4195-4223
[abs][Download PDF]
Implicit Regularization in ReLU Networks with the Square Loss
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4224-4258
[abs][Download PDF]
Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4259-4299
[abs][Download PDF]
Non-stationary Reinforcement Learning without Prior Knowledge: an Optimal Black-box Approach
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4300-4354
[abs][Download PDF]
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4355-4385
[abs][Download PDF]
The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4386-4437
[abs][Download PDF]
Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4438-4472
[abs][Download PDF]
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4473-4525
[abs][Download PDF]
Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov Noise
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4526-4527
[abs][Download PDF]
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4528-4531
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4532-4576
[abs][Download PDF]
A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4577-4632
[abs][Download PDF]
Benign Overfitting of Constant-Stepsize SGD for Linear Regression
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4633-4635
[abs][Download PDF]
Open Problem: Are all VC-classes CPAC learnable?
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4636-4641
[abs][Download PDF]
Open Problem: Is There an Online Learning Algorithm That Learns Whenever Online Learning Is Possible?
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4642-4646
[abs][Download PDF]
Open Problem: Tight Online Confidence Intervals for RKHS Elements
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4647-4652
[abs][Download PDF]
Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?
; Proceedings of Thirty Fourth Conference on Learning Theory, PMLR 134:4653-4658
[abs][Download PDF]
subscribe via RSS