conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5,312 papers

Papers per year

Papers

Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation AISTATS 2021
Experimental Design for Regret Minimization in Linear Bandits AISTATS 2021
Prediction with Finitely many Errors Almost Surely AISTATS 2021
Online Model Selection for Reinforcement Learning with Function Approximation AISTATS 2021
A Parameter-Free Algorithm for Misspecified Linear Contextual Bandits AISTATS 2021
Tracking Regret Bounds for Online Submodular Optimization AISTATS 2021
Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization AISTATS 2021
Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits AISTATS 2021
On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexity AISTATS 2021
Robust Learning under Strong Noise via SQs AISTATS 2021
Asymptotics of Ridge(less) Regression under General Source Condition AISTATS 2021
Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries AISTATS 2021
Does Invariant Risk Minimization Capture Invariance? AISTATS 2021
Sequential prediction under log-loss with side information ALT 2021
No-substitution k-means Clustering with Adversarial Order ALT 2021
Learning and Testing Irreducible Markov Chains via the $k$-Cover Time ALT 2021
Learning a mixture of two subspaces over finite fields ALT 2021
Last Round Convergence and No-Dynamic Regret in Asymmetric Repeated Games ALT 2021
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited ALT 2021
Adversarial Online Learning with Changing Action Sets: Efficient Algorithms with Approximate Regret Bounds ALT 2021
Near-tight Closure Bounds for the Littlestone and Threshold Dimensions ALT 2021
Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound ALT 2021
Characterizing the implicit bias via a primal-dual analysis ALT 2021
Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model ALT 2021
A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer ALT 2021