Online Algorithms

Competing against Adaptive Strategies in Online Learning via Hints AISTATS 2023 Competing Bandits in Time Varying Matching Markets L4DC 2023 Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms COLT 2023 Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets ICML 2023 Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games ICLR 2023 Delayed Feedback in Generalised Linear Bandits Revisited AISTATS 2023 Discrete-Smoothness in Online Algorithms with Predictions NeurIPS 2023 Dynamical Linear Bandits ICML 2023 Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination NeurIPS 2023 Efficient Explorative Key-Term Selection Strategies for Conversational Contextual Bandits AAAI 2023 Exploration for Free: How Does Reward Heterogeneity Improve Regret in Cooperative Multi-agent Bandits? UAI 2023 Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference AISTATS 2023 Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics JMLR 2023 Fast Online Node Labeling for Very Large Graphs ICML 2023 Federated Online and Bandit Convex Optimization ICML 2023 Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits AISTATS 2023 Geometric Barriers for Stable and Online Algorithms for Discrepancy Minimization COLT 2023 Gradient-Variation Bound for Online Convex Optimization with Constraints AAAI 2023 Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms NeurIPS 2023 Improved Dynamic Regret for Online Frank-Wolfe COLT 2023 Infinite Action Contextual Bandits with Reusable Data Exhaust ICML 2023 Information-Directed Selection for Top-Two Algorithms COLT 2023 Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition ICLR 2023 Learning to Boost Training by Periodic Nowcasting Near Future Weights ICML 2023 Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model ICML 2023