Online Learning

Heuristic-Guided Reinforcement Learning NeurIPS 2021 How to Learn when Data Reacts to Your Model: Performative Gradient Descent ICML 2021 Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications COLT 2021 Individual Fairness in Hindsight JMLR 2021 Joint Online Learning and Decision-making via Dual Mirror Descent ICML 2021 Learner-Private Convex Optimization ICML 2021 Learning-Augmented Dynamic Power Management with Multiple States via New Ski Rental Bounds NeurIPS 2021 Learning from Censored and Dependent Data: The case of Linear Dynamics COLT 2021 Learning in Markets: Greed Leads to Chaos but Following the Price is Right IJCAI 2021 Learning to Price Against a Moving Target ICML 2021 Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes JMLR 2021 Lenient Regret and Good-Action Identification in Gaussian Process Bandits ICML 2021 Lifelong Learning with Branching Experts ACML 2021 Linear and Kernel Classification in the Streaming Model: Improved Bounds for Heavy Hitters NeurIPS 2021 Locality Sensitive Teaching NeurIPS 2021 Majorizing Measures, Sequential Complexities, and Online Learning COLT 2021 Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations ACML 2021 Mean Field Equilibrium in Multi-Armed Bandit Game with Continuous Reward IJCAI 2021 Memory Efficient Online Meta Learning ICML 2021 Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning ICML 2021 MetaGrad: Adaptation using Multiple Learning Rates in Online Learning JMLR 2021 Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers NeurIPS 2021 Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition COLT 2021 Mixability made efficient: Fast online multiclass logistic regression NeurIPS 2021 Multi-armed Bandit Requiring Monotone Arm Sequences NeurIPS 2021