NeurIPS 2023 accepted papers on Bandits and online learning
130 of the 3,584 papers accepted at NeurIPS 2023 (3.6%) are on Bandits and online learning, compared with 4.9% at NeurIPS 2022. They fall into 4 topics.
See NeurIPS 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 · 52 papers
- CLIP-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments (3 citations)
- Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games (3 citations)
- Online Ad Procurement in Non-stationary Autobidding Worlds (3 citations)
- A Unified Approach for Maximizing Continuous DR-submodular Functions (2 citations)
- Double Auctions with Two-sided Bandit Feedback (2 citations)
- Meta-Learning Adversarial Bandit Algorithms (2 citations)
- On the Convergence of No-Regret Learning Dynamics in Time-Varying Games (2 citations)
- Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games (2 citations)
- An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits (1 citation)
- Dynamic Pricing and Learning with Bayesian Persuasion (1 citation)
- Learning and Collusion in Multi-unit Auctions (1 citation)
- Likelihood Ratio Confidence Sets for Sequential Decision Making (1 citation)
and 40 more in the interactive map.
Contextual bandits and Thompson sampling · 37 papers
- Failure-Aware Gaussian Process Optimization with Regret Bounds (2 citations)
- Online Clustering of Bandits with Misspecified User Models (2 citations)
- Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework (2 citations)
- Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization (2 citations)
- An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits (1 citation)
- Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments (1 citation)
- Cascading Contextual Assortment Bandits (1 citation)
- Contextual Bandits and Imitation Learning with Preference-Based Active Queries (1 citation)
- Contextual Gaussian Process Bandits with Neural Networks (1 citation)
- Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards (1 citation)
- Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts (1 citation)
- Noise-Adaptive Thompson Sampling for Linear Contextual Bandits (1 citation)
and 25 more in the interactive map.
Multi-armed bandits · 28 papers
- Adaptive Algorithms for Relaxed Pareto Set Identification (3 citations)
- Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption (3 citations)
- Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards (2 citations)
- Non-Stationary Bandits with Auto-Regressive Temporal Dependency (2 citations)
- An active learning framework for multi-group mean estimation (1 citation)
- Best Arm Identification with Fixed Budget: A Large Deviation Perspective (1 citation)
- Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits (1 citation)
- Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation (1 citation)
- Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms (1 citation)
- Improving the Knowledge Gradient Algorithm (1 citation)
- An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
- Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits
and 16 more in the interactive map.
RL theory and MDPs · 13 papers
- Model-Free Reinforcement Learning with the Decision-Estimation Coefficient (2 citations)
- Provably Safe Reinforcement Learning with Step-wise Violation Constraints (2 citations)
- Kernelized Reinforcement Learning with Order Optimal Regret Bounds (1 citation)
- No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions (1 citation)
- Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation (1 citation)
- Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time (1 citation)
- Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
- Dynamic Regret of Adversarial Linear Mixture MDPs
- Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
- Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
- Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
- The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning
and 1 more in the interactive map.