NeurIPS 2019 accepted papers on Bandits and online learning
80 of the 1,429 papers accepted at NeurIPS 2019 (5.6%) are on Bandits and online learning, compared with 4.3% at NeurIPS 2018. They fall into 4 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Online convex optimization and games · 28 papers
- Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions (71 citations)
- Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis (54 citations)
- Weighted Linear Bandits for Non-Stationary Environments (52 citations)
- Logarithmic Regret for Online Control (47 citations)
- Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization (40 citations)
- Online-Within-Online Meta-Learning (22 citations)
- Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback (20 citations)
- Online EXP3 Learning in Adversarial Bandits with Delayed Feedback (19 citations)
- Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes (17 citations)
- Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing (12 citations)
- Online Forecasting of Total-Variation-bounded Sequences (12 citations)
- Connections Between Mirror Descent, Thompson Sampling and the Information Ratio (11 citations)
and 16 more in the interactive map.
Multi-armed bandits · 25 papers
- Decentralized Cooperative Stochastic Bandits (67 citations)
- Batched Multi-armed Bandits Problem (41 citations)
- Linear Stochastic Bandits Under Safety Constraints (40 citations)
- Pure Exploration with Multiple Correct Answers (35 citations)
- Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards (29 citations)
- Are sample means in multi-armed bandits positively or negatively biased? (25 citations)
- Bootstrapping Upper Confidence Bound (24 citations)
- Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits (16 citations)
- SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits (15 citations)
- Phase Transitions and Cyclic Phenomena in Bandits with Switching Constraints (13 citations)
- Optimal Best Markovian Arm Identification with Fixed Confidence (11 citations)
- Blocking Bandits (9 citations)
and 13 more in the interactive map.
Contextual bandits and Thompson sampling · 16 papers
- Model Selection for Contextual Bandits (40 citations)
- Learning in Generalized Linear Contextual Bandits with Stochastic Delays (30 citations)
- Offline Contextual Bandits with High Probability Fairness Guarantees (26 citations)
- Doubly-Robust Lasso Bandit (23 citations)
- Thompson Sampling for Multinomial Logit Contextual Bandits (23 citations)
- Stochastic Bandits with Context Distributions (17 citations)
- Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems (15 citations)
- Thompson Sampling and Approximate Inference (14 citations)
- No-Regret Learning in Unknown Games with Correlated Payoffs (12 citations)
- Sequential Experimental Design for Transductive Linear Bandits (9 citations)
- Bayesian Optimization under Heavy-tailed Payoffs (8 citations)
- Semi-Parametric Dynamic Contextual Pricing (7 citations)
and 4 more in the interactive map.
RL theory and MDPs · 11 papers
- Provably Efficient Q-Learning with Low Switching Cost (25 citations)
- Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs (24 citations)
- Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function (22 citations)
- Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs (20 citations)
- Worst-Case Regret Bounds for Exploration via Randomized Value Functions (14 citations)
- Information-Theoretic Confidence Bounds for Reinforcement Learning (13 citations)
- Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function (7 citations)
- Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives (7 citations)
- Large Scale Markov Decision Processes with Changing Rewards (6 citations)
- Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards (1 citation)
- Regret Bounds for Learning State Representations in Reinforcement Learning (1 citation)
