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

Learning Theory

5,312 papers

Papers per year

Papers

A Quantitative Geometric Approach to Neural-Network Smoothness NIPS 2022
On the generalization of learning algorithms that do not converge NIPS 2022
Invariance-Aware Randomized Smoothing Certificates NIPS 2022
Graph Neural Network Bandits NIPS 2022
Towards Understanding Grokking: An Effective Theory of Representation Learning NIPS 2022
Globally Gated Deep Linear Networks NIPS 2022
On the Double Descent of Random Features Models Trained with SGD NIPS 2022
Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve NIPS 2022
Learning (Very) Simple Generative Models Is Hard NIPS 2022
A Regret-Variance Trade-Off in Online Learning NIPS 2022
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis NIPS 2022
On the Complexity of Adversarial Decision Making NIPS 2022
Contextual Bandits with Knapsacks for a Conversion Model NIPS 2022
Robustness to Label Noise Depends on the Shape of the Noise Distribution NIPS 2022
Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL NIPS 2022
Score-Based Generative Models Detect Manifolds NIPS 2022
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions NIPS 2022
Reinforcement Learning with Logarithmic Regret and Policy Switches NIPS 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NIPS 2022
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs NIPS 2022
Learning Partial Equivariances From Data NIPS 2022
On Margin Maximization in Linear and ReLU Networks NIPS 2022
Incentivizing Combinatorial Bandit Exploration NIPS 2022
Is Out-of-Distribution Detection Learnable? NIPS 2022
Theoretical analysis of deep neural networks for temporally dependent observations NIPS 2022