← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient ICML 2016
The Information-Theoretic Requirements of Subspace Clustering with Missing Data ICML 2016
PAC learning of Probabilistic Automaton based on the Method of Moments ICML 2016
PAC Lower Bounds and Efficient Algorithms for The Max K-Armed Bandit Problem ICML 2016
Anytime Exploration for Multi-armed Bandits using Confidence Information ICML 2016
Anytime optimal algorithms in stochastic multi-armed bandits ICML 2016
Barron and Cover’s Theory in Supervised Learning and its Application to Lasso ICML 2016
On the Power and Limits of Distance-Based Learning ICML 2016
Generalization Properties and Implicit Regularization for Multiple Passes SGM ICML 2016
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity ICML 2016
Pricing a Low-regret Seller ICML 2016
Learnability of Non-I.I.D. ACML 2016
An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning JMLR 2016
Online PCA with Optimal Regret JMLR 2016
Machine Learning in an Auction Environment JMLR 2016
The Optimal Sample Complexity of PAC Learning JMLR 2016
On the Characterization of a Class of Fisher-Consistent Loss Functions and its Application to Boosting JMLR 2016
Learning from Survey Training Samples: Rate Bounds for Horvitz-Thompson Risk Minimizers ACML 2016
Graph Connectivity in Noisy Sparse Subspace Clustering AISTATS 2016
Learning Taxonomy Adaptation in Large-scale Classification JMLR 2016
Metric Learning as Convex Combinations of Local Models With Generalization Guarantees CVPR 2016
Second-order Quantile Methods for Experts and Combinatorial Games COLT 2015
Surrogate regret bounds for generalized classification performance metrics ACML 2015
Open Problem: Recursive Teaching Dimension Versus VC Dimension COLT 2015
Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning ICML 2015