Online Learning

Learning Halfspaces with the Zero-One Loss: Time-Accuracy Tradeoffs NeurIPS 2012 Learning Valuation Functions COLT 2012 Mirror Descent Meets Fixed Share (and feels no regret) NeurIPS 2012 Multi-armed Bandit Problems with History AISTATS 2012 Near-Optimal Algorithms for Online Matrix Prediction COLT 2012 No-Regret Algorithms for Unconstrained Online Convex Optimization NeurIPS 2012 Online allocation and homogeneous partitioning for piecewise constant mean-approximation NeurIPS 2012 Online Clustering with Experts AISTATS 2012 Online Incremental Feature Learning with Denoising Autoencoders AISTATS 2012 Online L1-Dictionary Learning with Application to Novel Document Detection NeurIPS 2012 Online Learning in the Embedded Manifold of Low-rank Matrices JMLR 2012 Online Learning of a Dirichlet Process Mixture of Generalized Dirichlet Distributions for Simultaneous Clustering and Localized Feature Selection ACML 2012 Online Optimization with Gradual Variations COLT 2012 Online Rank Aggregation ACML 2012 Online Regret Bounds for Undiscounted Continuous Reinforcement Learning NeurIPS 2012 On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization NeurIPS 2012 On Multilabel Classification and Ranking with Partial Feedback NeurIPS 2012 Open Problem: Better Bounds for Online Logistic Regression COLT 2012 Optimal Regularized Dual Averaging Methods for Stochastic Optimization NeurIPS 2012 Putting Bayes to sleep NeurIPS 2012 Relax and Randomize : From Value to Algorithms NeurIPS 2012 Risk-Aversion in Multi-armed Bandits NeurIPS 2012 Stochastic Gradient Descent with Only One Projection NeurIPS 2012 The adversarial stochastic shortest path problem with unknown transition probabilities AISTATS 2012 The Optimality of Jeffreys Prior for Online Density Estimation and the Asymptotic Normality of Maximum Likelihood Estimators COLT 2012