ICML 2018 accepted papers on Bandits and online learning
24 of the 623 papers accepted at ICML 2018 (3.9%) are on Bandits and online learning, compared with 5.7% at ICML 2017. They fall into 4 topics.
See ICML 2018 in the interactive map
Submitting to ICML? 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
Contextual bandits and Thompson sampling · 9 papers
- Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems (52 citations)
- Thompson Sampling for Combinatorial Semi-Bandits (46 citations)
- Practical Contextual Bandits with Regression Oracles (45 citations)
- Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits (20 citations)
- Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits (12 citations)
- Semiparametric Contextual Bandits (12 citations)
- Tight Regret Bounds for Bayesian Optimization in One Dimension (7 citations)
- Causal Bandits with Propagating Inference (5 citations)
- Mitigating Bias in Adaptive Data Gathering via Differential Privacy (4 citations)
Online convex optimization and games · 7 papers
- Dynamic Regret of Strongly Adaptive Methods (33 citations)
- Online Learning with Abstention (22 citations)
- Online Linear Quadratic Control (18 citations)
- Streaming Principal Component Analysis in Noisy Setting (10 citations)
- Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer (7 citations)
- Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games
- Competitive Caching with Machine Learned Advice
Multi-armed bandits · 6 papers
- Bandits with Delayed, Aggregated Anonymous Feedback (56 citations)
- Best Arm Identification in Linear Bandits with Linear Dimension Dependency (32 citations)
- Firing Bandits: Optimizing Crowdfunding (8 citations)
- Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors (4 citations)
- Feasible Arm Identification (3 citations)
- Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Covariates
