ICML 2017 accepted papers on Bandits and online learning
25 of the 435 papers accepted at ICML 2017 (5.7%) are on Bandits and online learning, compared with 7.5% at ICML 2016. They fall into 4 topics.
See ICML 2017 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 · 10 papers
- Projection-free Distributed Online Learning in Networks (48 citations)
- The Price of Differential Privacy for Online Learning (46 citations)
- Near-Optimal Design of Experiments via Regret Minimization (36 citations)
- Emulating the Expert: Inverse Optimization through Online Learning (28 citations)
- Second-Order Kernel Online Convex Optimization with Adaptive Sketching (24 citations)
- Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU (22 citations)
- Model-Independent Online Learning for Influence Maximization (18 citations)
- Online Learning with Local Permutations and Delayed Feedback (4 citations)
- Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP (2 citations)
- Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret (1 citation)
Multi-armed bandits · 7 papers
- Automated Curriculum Learning for Neural Networks (37 citations)
- On Kernelized Multi-armed Bandits (22 citations)
- Multi-objective Bandits: Optimizing the Generalized Gini Index (20 citations)
- Identifying Best Interventions through Online Importance Sampling (19 citations)
- Adaptive Multiple-Arm Identification (10 citations)
- Dueling Bandits with Weak Regret (6 citations)
- Identify the Nash Equilibrium in Static Games with Random Payoffs (3 citations)
Contextual bandits and Thompson sampling · 6 papers
- Provably Optimal Algorithms for Generalized Linear Contextual Bandits (144 citations)
- Online Learning to Rank in Stochastic Click Models (55 citations)
- Safety-Aware Algorithms for Adversarial Contextual Bandit (35 citations)
- Optimal and Adaptive Off-policy Evaluation in Contextual Bandits (19 citations)
- On Context-Dependent Clustering of Bandits (7 citations)
- Active Learning for Accurate Estimation of Linear Models (2 citations)
