ICLR 2024 accepted papers on Bandits and online learning
25 of the 2,259 papers accepted at ICLR 2024 (1.1%) are on Bandits and online learning, compared with 1.3% at ICLR 2023. They fall into 4 topics.
See ICLR 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 · 9 papers
- Algorithms for Caching and MTS with reduced number of predictions (1 citation)
- Bandits with Replenishable Knapsacks: the Best of both Worlds (1 citation)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice
- Learning Optimal Contracts: How to Exploit Small Action Spaces
- Learning Thresholds with Latent Values and Censored Feedback
- Oracle Efficient Algorithms for Groupwise Regret
- Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization
- Dynamic Discounted Counterfactual Regret Minimization
- Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
Contextual bandits and Thompson sampling · 6 papers
- Neural Active Learning Beyond Bandits (1 citation)
- Cascading Reinforcement Learning
- Contextual Bandits with Online Neural Regression
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits
- A Discretization Framework for Robust Contextual Stochastic Optimization
RL theory and MDPs · 6 papers
- Demystifying Linear MDPs and Novel Dynamics Aggregation Framework
- Horizon-Free Regret for Linear Markov Decision Processes
- Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
- Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
- Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
Multi-armed bandits · 4 papers
- Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation (1 citation)
- Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback (1 citation)
- Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit (1 citation)
- Fixed-Budget Differentially Private Best Arm Identification (1 citation)