ICML 2024 accepted papers on Bandits and online learning
79 of the 2,610 papers accepted at ICML 2024 (3.0%) are on Bandits and online learning, compared with 5.6% at ICML 2023. They fall into 4 topics.
See ICML 2024 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 · 32 papers
- Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning (1 citation)
- Non-clairvoyant Scheduling with Partial Predictions (1 citation)
- Online Learning in Betting Markets: Profit versus Prediction (1 citation)
- Online Learning under Budget and ROI Constraints via Weak Adaptivity (1 citation)
- Online Linear Regression in Dynamic Environments via Discounting (1 citation)
- Performative Prediction with Bandit Feedback: Learning through Reparameterization (1 citation)
- A General Online Algorithm for Optimizing Complex Performance Metrics
- Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
- Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods
- Efficient Online Set-valued Classification with Bandit Feedback
- Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
- Incentivized Learning in Principal-Agent Bandit Games
and 20 more in the interactive map.
Contextual bandits and Thompson sampling · 22 papers
- $\mathtt{VITS}$ : Variational Inference Thompson Sampling for contextual bandits (1 citation)
- A Contextual Combinatorial Bandit Approach to Negotiation (1 citation)
- Online Matrix Completion: A Collaborative Approach with Hott Items (1 citation)
- Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds (1 citation)
- Adaptively Learning to Select-Rank in Online Platforms
- Bayesian Regret Minimization in Offline Bandits
- Borda Regret Minimization for Generalized Linear Dueling Bandits
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
- Efficient Contextual Bandits with Uninformed Feedback Graphs
- Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
- Feel-Good Thompson Sampling for Contextual Dueling Bandits
and 10 more in the interactive map.
RL theory and MDPs · 16 papers
- No-Regret Reinforcement Learning in Smooth MDPs (1 citation)
- Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret (1 citation)
- A General Framework for Sequential Decision-Making under Adaptivity Constraints
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling
- Eluder-based Regret for Stochastic Contextual MDPs
- More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning
- Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
- Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
- Prospective Side Information for Latent MDPs
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
- Rate-Optimal Policy Optimization for Linear Markov Decision Processes
- Reinforcement Learning and Regret Bounds for Admission Control
and 4 more in the interactive map.
Multi-armed bandits · 9 papers
- Adversarial Attacks on Combinatorial Multi-Armed Bandits (1 citation)
- Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond (1 citation)
- On Interpolating Experts and Multi-Armed Bandits (1 citation)
- Best Arm Identification for Stochastic Rising Bandits
- Federated Combinatorial Multi-Agent Multi-Armed Bandits
- Graph-Triggered Rising Bandits
- Leveraging (Biased) Information: Multi-armed Bandits with Offline Data
- On Multi-Armed Bandit with Impatient Arms
- On Universally Optimal Algorithms for A/B Testing