NeurIPS 2025 accepted papers on Bandits and online learning
130 of the 5,812 papers accepted at NeurIPS 2025 (2.2%) are on Bandits and online learning, compared with 2.8% at NeurIPS 2024. They fall into 4 topics.
See NeurIPS 2025 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 · 68 papers
- Learning to price with resource constraints: from full information to machine-learned prices (3 citations)
- Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift (2 citations)
- On the Universal Near Optimality of Hedge in Combinatorial Settings (1 citation)
- Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound (1 citation)
- Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making (1 citation)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (1 citation)
- Replicable Online Learning (1 citation)
- $O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
- A Bayesian Approach to Contextual Dynamic Pricing using the Proportional Hazards Model with Discrete Price Data
- Agnostic Continuous-Time Online Learning
- An Ellipsoid Algorithm for Online Convex Optimization
- Bandit and Delayed Feedback in Online Structured Prediction
and 56 more in the interactive map.
Contextual bandits and Thompson sampling · 32 papers
- Constrained Linear Thompson Sampling (1 citation)
- A Novel General Framework for Sharp Lower Bounds in Succinct Stochastic Bandits
- Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
- Causal LLM Routing: End-to-End Regret Minimization from Observational Data
- Contextual Online Pricing with (Biased) Offline Data
- Contextual Thompson Sampling via Generation of Missing Data
- Diffusion Models Meet Contextual Bandits
- Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles
- Exploration via Feature Perturbation in Contextual Bandits
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown
- From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards
and 20 more in the interactive map.
Multi-armed bandits · 23 papers
- Federated Multi-armed Bandits with Efficient Bit-Level Communications (1 citation)
- A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
- Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation
- Balancing Performance and Costs in Best Arm Identification
- Bandit Guided Submodular Curriculum for Adaptive Subset Selection
- Constrained Best Arm Identification
- Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
- Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks
- Does Stochastic Gradient really succeed for bandits?
- Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits
- FraPPE: Fast and Efficient Preference-Based Pure Exploration
and 11 more in the interactive map.
RL theory and MDPs · 7 papers
- Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
- Eluder dimension: localise it!
- No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
- Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning
- Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
- REINFORCE Converges to Optimal Policies with Any Learning Rate
- Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs