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

Learning Theory

5,312 papers

Papers per year

Papers

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels ICML 2021
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity ICML 2021
Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs ICML 2021
Adaptive Sampling for Best Policy Identification in Markov Decision Processes ICML 2021
Leveraging Non-uniformity in First-order Non-convex Optimization ICML 2021
A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions ICML 2021
Fast active learning for pure exploration in reinforcement learning ICML 2021
UCB Momentum Q-learning: Correcting the bias without forgetting ICML 2021
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization ICML 2021
Generalization Guarantees for Neural Architecture Search with Train-Validation Split ICML 2021
Leveraging Good Representations in Linear Contextual Bandits ICML 2021
Rissanen Data Analysis: Examining Dataset Characteristics via Description Length ICML 2021
A Probabilistic Approach to Neural Network Pruning ICML 2021
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions ICML 2021
Implicit Regularization in Tensor Factorization ICML 2021
Align, then memorise: the dynamics of learning with feedback alignment ICML 2021
On the Predictability of Pruning Across Scales ICML 2021
Multi-group Agnostic PAC Learnability ICML 2021
Towards Understanding Learning in Neural Networks with Linear Teachers ICML 2021
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise ICML 2021
PAC-Learning for Strategic Classification ICML 2021
Understanding self-supervised learning dynamics without contrastive pairs ICML 2021
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation ICML 2021
On the Optimality of Batch Policy Optimization Algorithms ICML 2021