ICML 2019 accepted papers on Bandits and online learning
41 of the 774 papers accepted at ICML 2019 (5.3%) are on Bandits and online learning, compared with 3.9% at ICML 2018. They fall into 4 topics.
See ICML 2019 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
Online convex optimization and games · 21 papers
- Online Meta-Learning (93 citations)
- Online Control with Adversarial Disturbances (54 citations)
- Online Algorithms for Rent-Or-Buy with Expert Advice (43 citations)
- Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ Regret (35 citations)
- Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously (33 citations)
- Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints (26 citations)
- Deep Counterfactual Regret Minimization (21 citations)
- Adaptive Regret of Convex and Smooth Functions (17 citations)
- Incremental Randomized Sketching for Online Kernel Learning (14 citations)
- Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games (13 citations)
- Regret Circuits: Composability of Regret Minimizers (13 citations)
- Adaptive Scale-Invariant Online Algorithms for Learning Linear Models (12 citations)
and 9 more in the interactive map.
Contextual bandits and Thompson sampling · 9 papers
- On the Design of Estimators for Bandit Off-Policy Evaluation (17 citations)
- Bilinear Bandits with Low-rank Structure (13 citations)
- Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback (12 citations)
- Online Learning to Rank with Features (10 citations)
- Adaptive Sensor Placement for Continuous Spaces (8 citations)
- Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model (7 citations)
- Exploiting structure of uncertainty for efficient matroid semi-bandits (7 citations)
- Target Tracking for Contextual Bandits: Application to Demand Side Management (4 citations)
- Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging (3 citations)
Multi-armed bandits · 8 papers
- Data Poisoning Attacks on Stochastic Bandits (29 citations)
- Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards (15 citations)
- Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits (12 citations)
- An Optimal Private Stochastic-MAB Algorithm based on Optimal Private Stopping Rule (10 citations)
- Decentralized Exploration in Multi-Armed Bandits (7 citations)
- Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits (5 citations)
- PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits (5 citations)
- Correlated bandits or: How to minimize mean-squared error online (1 citation)
