NeurIPS 2022 accepted papers on Bandits and online learning
142 of the 2,901 papers accepted at NeurIPS 2022 (4.9%) are on Bandits and online learning, compared with 5.5% at NeurIPS 2021. They fall into 4 topics.
See NeurIPS 2022 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Online convex optimization and games · 66 papers
- Online Bipartite Matching with Advice: Tight Robustness-Consistency Tradeoffs for the Two-Stage Model (13 citations)
- Online Learning and Pricing for Network Revenue Management with Reusable Resources (7 citations)
- Lipschitz Bandits with Batched Feedback (6 citations)
- Non-stationary Bandits with Knapsacks (6 citations)
- Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and Beyond (6 citations)
- A Unifying Framework for Online Optimization with Long-Term Constraints (5 citations)
- Better Best of Both Worlds Bounds for Bandits with Switching Costs (5 citations)
- Distributed Online Convex Optimization with Compressed Communication (4 citations)
- Improved Algorithms for Neural Active Learning (4 citations)
- Near-Optimal No-Regret Learning Dynamics for General Convex Games (4 citations)
- On the Complexity of Adversarial Decision Making (4 citations)
- Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness (3 citations)
and 54 more in the interactive map.
Contextual bandits and Thompson sampling · 31 papers
- Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms (6 citations)
- Tsetlin Machine for Solving Contextual Bandit Problems (5 citations)
- Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions (4 citations)
- A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits (3 citations)
- Conformal Off-Policy Prediction in Contextual Bandits (3 citations)
- Adaptively Exploiting d-Separators with Causal Bandits (2 citations)
- An Analysis of Ensemble Sampling (2 citations)
- Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems (2 citations)
- Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds (2 citations)
- Communication Efficient Distributed Learning for Kernelized Contextual Bandits (2 citations)
- Group Meritocratic Fairness in Linear Contextual Bandits (2 citations)
- Incentivizing Combinatorial Bandit Exploration (2 citations)
and 19 more in the interactive map.
RL theory and MDPs · 23 papers
- Provably Efficient Model-Free Constrained RL with Linear Function Approximation (6 citations)
- Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs (3 citations)
- Exponential Family Model-Based Reinforcement Learning via Score Matching (2 citations)
- IMED-RL: Regret optimal learning of ergodic Markov decision processes (2 citations)
- Near-Optimal Randomized Exploration for Tabular Markov Decision Processes (2 citations)
- Regret Bounds for Information-Directed Reinforcement Learning (2 citations)
- Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback (1 citation)
- Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs (1 citation)
- Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets (1 citation)
- Learning Infinite-Horizon Average-Reward Restless Multi-Action Bandits via Index Awareness (1 citation)
- Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning (1 citation)
- Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback (1 citation)
and 11 more in the interactive map.
Multi-armed bandits · 22 papers
- On Kernelized Multi-Armed Bandits with Constraints (11 citations)
- Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits (7 citations)
- Maximizing and Satisficing in Multi-armed Bandits with Graph Information (4 citations)
- Near-Optimal Collaborative Learning in Bandits (4 citations)
- Top Two Algorithms Revisited (3 citations)
- Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget (2 citations)
- Instance-optimal PAC Algorithms for Contextual Bandits (2 citations)
- MABSplit: Faster Forest Training Using Multi-Armed Bandits (2 citations)
- Multi-Fidelity Best-Arm Identification (2 citations)
- A Simple and Optimal Policy Design for Online Learning with Safety against Heavy-tailed Risk (1 citation)
- Active Learning with Safety Constraints (1 citation)
- Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification (1 citation)
and 10 more in the interactive map.
