Online Algorithms

Second Order Methods for Bandit Optimization and Control COLT 2024 Seer: Enabling Future-Aware Online Caching in Networked Systems NSDI 2024 Sequential Kernel Goodness-of-fit Testing ICML 2024 Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood NeurIPS 2024 Sifter: An Inversion-Free and Large-Capacity Programmable Packet Scheduler NSDI 2024 Simple online learning with consistent oracle COLT 2024 Small-loss Adaptive Regret for Online Convex Optimization ICML 2024 SmartTransit.AI: A Dynamic Paratransit and Microtransit Application IJCAI 2024 Smoothness-Adaptive Dynamic Pricing with Nonparametric Demand Learning AISTATS 2024 Sparse Recovery With Multiple Data Streams: An Adaptive Sequential Testing Approach JMLR 2024 Sparsity-Agnostic Linear Bandits with Adaptive Adversaries NeurIPS 2024 Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling NeurIPS 2024 Stakeholder-oriented Decision Support for Auction-based Federated Learning IJCAI 2024 Stochastic Multi-Armed Bandits with Strongly Reward-Dependent Delays AISTATS 2024 Strategic Linear Contextual Bandits NeurIPS 2024 Strategic Recommendation: Revenue Optimal Matching for Online Platforms (Student Abstract) AAAI 2024 Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model JMLR 2024 Sum-max Submodular Bandits AISTATS 2024 Symmetric Linear Bandits with Hidden Symmetry NeurIPS 2024 Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting NeurIPS 2024 Testing Calibration in Nearly-Linear Time NeurIPS 2024 Testing the Feasibility of Linear Programs with Bandit Feedback ICML 2024 The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits COLT 2024 The Predicted-Updates Dynamic Model: Offline, Incremental, and Decremental to Fully Dynamic Transformations COLT 2024 The Real Price of Bandit Information in Multiclass Classification COLT 2024