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

Learning Theory

5,312 papers

Papers per year

Papers

Non-uniform Consistency of Online Learning with Random Sampling ALT 2021
SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021
Functions with average smoothness: structure, algorithms, and learning COLT 2021
Optimal Dynamic Regret in Exp-Concave Online Learning COLT 2021
Reconstructing weighted voting schemes from partial information about their power indices COLT 2021
Online Learning from Optimal Actions COLT 2021
Majorizing Measures, Sequential Complexities, and Online Learning COLT 2021
Statistical Query Algorithms and Low Degree Tests Are Almost Equivalent COLT 2021
Fast Rates for Structured Prediction COLT 2021
Learning and testing junta distributions with sub cube conditioning COLT 2021
From Local Pseudorandom Generators to Hardness of Learning COLT 2021
Weak learning convex sets under normal distributions COLT 2021
Learning sparse mixtures of permutations from noisy information COLT 2021
Agnostic Proper Learning of Halfspaces under Gaussian Marginals COLT 2021
The Optimality of Polynomial Regression for Agnostic Learning under Gaussian Marginals in the SQ Model COLT 2021
Boosting in the Presence of Massart Noise COLT 2021
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning COLT 2021
Sequential prediction under log-loss and misspecification COLT 2021
Convergence rates and approximation results for SGD and its continuous-time counterpart COLT 2021
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes COLT 2021
Generalizing Complex Hypotheses on Product Distributions: Auctions, Prophet Inequalities, and Pandora’s Problem COLT 2021
Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games COLT 2021
Bounded Memory Active Learning through Enriched Queries COLT 2021
Fast Rates for the Regret of Offline Reinforcement Learning COLT 2021
Streaming k-PCA: Efficient guarantees for Oja’s algorithm, beyond rank-one updates COLT 2021