ICML 2023 accepted papers on Bandits and online learning
105 of the 1,865 papers accepted at ICML 2023 (5.6%) are on Bandits and online learning, compared with 6.2% at ICML 2022. They fall into 4 topics.
See ICML 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Online convex optimization and games · 48 papers
- Improved Online Conformal Prediction via Strongly Adaptive Online Learning (11 citations)
- Multi-channel Autobidding with Budget and ROI Constraints (9 citations)
- Active Ranking of Experts Based on their Performances in Many Tasks (2 citations)
- Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets (2 citations)
- Online Learning in Stackelberg Games with an Omniscient Follower (2 citations)
- Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization (2 citations)
- Regret Minimization and Convergence to Equilibria in General-sum Markov Games (2 citations)
- Adapting to game trees in zero-sum imperfect information games (1 citation)
- Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits (1 citation)
- Learning to Bid in Repeated First-Price Auctions with Budgets (1 citation)
- Minimalistic Predictions to Schedule Jobs with Online Precedence Constraints (1 citation)
- Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion (1 citation)
and 36 more in the interactive map.
Contextual bandits and Thompson sampling · 26 papers
- Contextual Combinatorial Bandits with Probabilistically Triggered Arms (3 citations)
- Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits (3 citations)
- Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost (2 citations)
- Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret Bounds (2 citations)
- An Information-Theoretic Analysis of Nonstationary Bandit Learning (1 citation)
- Incentivizing Exploration with Linear Contexts and Combinatorial Actions (1 citation)
- Multi-Task Off-Policy Learning from Bandit Feedback (1 citation)
- Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits (1 citation)
- PAC-Bayesian Offline Contextual Bandits With Guarantees (1 citation)
- Provably and Practically Efficient Neural Contextual Bandits (1 citation)
- Additive Causal Bandits with Unknown Graph
- Combinatorial Neural Bandits
and 14 more in the interactive map.
RL theory and MDPs · 16 papers
- Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents (5 citations)
- A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints (2 citations)
- Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation (1 citation)
- Lower Bounds for Learning in Revealing POMDPs (1 citation)
- Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR (1 citation)
- Best of Both Worlds Policy Optimization
- Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback
- Does Sparsity Help in Learning Misspecified Linear Bandits?
- Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation
- Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes
- Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
- Refined Regret for Adversarial MDPs with Linear Function Approximation
and 4 more in the interactive map.
Multi-armed bandits · 15 papers
- Pareto Regret Analyses in Multi-objective Multi-armed Bandit (3 citations)
- Competing for Shareable Arms in Multi-Player Multi-Armed Bandits (2 citations)
- A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback (1 citation)
- Bayesian Design Principles for Frequentist Sequential Learning (1 citation)
- Statistical Inference on Multi-armed Bandits with Delayed Feedback (1 citation)
- Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
- Communication-Constrained Bandits under Additive Gaussian Noise
- Doubly Adversarial Federated Bandits
- Multi-task Representation Learning for Pure Exploration in Linear Bandits
- Multiplier Bootstrap-based Exploration
- Revisiting Simple Regret: Fast Rates for Returning a Good Arm
- Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits
and 3 more in the interactive map.