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

Learning Theory

5,312 papers

Papers per year

Papers

Generalization Bounds for Data-Driven Numerical Linear Algebra COLT 2022
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data COLT 2022
Minimax Regret Optimization for Robust Machine Learning under Distribution Shift COLT 2022
Offline Reinforcement Learning with Realizability and Single-policy Concentrability COLT 2022
Realizable Learning is All You Need COLT 2022
Minimax Regret on Patterns Using Kullback-Leibler Divergence Covering COLT 2022
Uniform Stability for First-Order Empirical Risk Minimization COLT 2022
Single Trajectory Nonparametric Learning of Nonlinear Dynamics COLT 2022
On characterizations of learnability with computable learners COLT 2022
Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond COLT 2022
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation COLT 2022
Generalization Bounds via Convex Analysis COLT 2022
Hardness of Maximum Likelihood Learning of DPPs COLT 2022
Learning to Control Linear Systems can be Hard COLT 2022
Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies COLT 2022
Chained generalisation bounds COLT 2022
Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise COLT 2022
Faster online calibration without randomization: interval forecasts and the power of two choices COLT 2022
Scale-free Unconstrained Online Learning for Curved Losses COLT 2022
The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks COLT 2022
Eigenspace Restructuring: A Principle of Space and Frequency in Neural Networks COLT 2022
Strong Memory Lower Bounds for Learning Natural Models COLT 2022
On the power of adaptivity in statistical adversaries COLT 2022
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information COLT 2022
Complete Policy Regret Bounds for Tallying Bandits COLT 2022