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

Learning Theory

5,312 papers

Papers per year

Papers

The Pareto Frontier of model selection for general Contextual Bandits NIPS 2021
Learning curves of generic features maps for realistic datasets with a teacher-student model NIPS 2021
Supervising the Transfer of Reasoning Patterns in VQA NIPS 2021
Training Neural Networks is ER-complete NIPS 2021
Decentralized Learning in Online Queuing Systems NIPS 2021
On the Sample Complexity of Learning under Geometric Stability NIPS 2021
Taxonomizing local versus global structure in neural network loss landscapes NIPS 2021
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NIPS 2021
Bandit Phase Retrieval NIPS 2021
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations NIPS 2021
Support Recovery of Sparse Signals from a Mixture of Linear Measurements NIPS 2021
Tighter Expected Generalization Error Bounds via Wasserstein Distance NIPS 2021
Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics NIPS 2021
Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning NIPS 2021
Stochastic bandits with groups of similar arms. NIPS 2021
Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization NIPS 2021
Grounding inductive biases in natural images: invariance stems from variations in data NIPS 2021
Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations NIPS 2021
Provably efficient multi-task reinforcement learning with model transfer NIPS 2021
Algorithmic stability and generalization of an unsupervised feature selection algorithm NIPS 2021
On learning sparse vectors from mixture of responses NIPS 2021
Hessian Eigenspectra of More Realistic Nonlinear Models NIPS 2021
On the Provable Generalization of Recurrent Neural Networks NIPS 2021
Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning NIPS 2021
The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition NIPS 2021