ICML 2016 accepted papers on Bandits and online learning
24 of the 322 papers accepted at ICML 2016 (7.5%) are on Bandits and online learning. They fall into 3 topics.
See ICML 2016 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 · 10 papers
- Distributed Clustering of Linear Bandits in Peer to Peer Networks (96 citations)
- BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits (69 citations)
- DCM Bandits: Learning to Rank with Multiple Clicks (55 citations)
- Efficient Algorithms for Adversarial Contextual Learning (39 citations)
- Online Stochastic Linear Optimization under One-bit Feedback (30 citations)
- Bounded Off-Policy Evaluation with Missing Data for Course Recommendation and Curriculum Design (16 citations)
- The Knowledge Gradient for Sequential Decision Making with Stochastic Binary Feedbacks (14 citations)
- No-Regret Algorithms for Heavy-Tailed Linear Bandits (12 citations)
- Barron and Cover’s Theory in Supervised Learning and its Application to Lasso (3 citations)
- Contextual Combinatorial Cascading Bandits
Multi-armed bandits · 8 papers
- An optimal algorithm for the Thresholding Bandit Problem (64 citations)
- Conservative Bandits (27 citations)
- Anytime optimal algorithms in stochastic multi-armed bandits (26 citations)
- Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm (8 citations)
- Anytime Exploration for Multi-armed Bandits using Confidence Information (4 citations)
- PAC Lower Bounds and Efficient Algorithms for The Max K-Armed Bandit Problem (4 citations)
- Multi-Player Bandits – a Musical Chairs Approach (3 citations)
- Scalable Discrete Sampling as a Multi-Armed Bandit Problem (3 citations)
Online convex optimization and games · 6 papers
- Adaptive Algorithms for Online Convex Optimization with Long-term Constraints (82 citations)
- Online Learning with Feedback Graphs Without the Graphs (22 citations)
- Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient (17 citations)
- Shifting Regret, Mirror Descent, and Matrices (9 citations)
- Pricing a Low-regret Seller (6 citations)
- Heteroscedastic Sequences: Beyond Gaussianity (2 citations)
