NeurIPS 2016 accepted papers on Bandits and online learning
37 of the 570 papers accepted at NeurIPS 2016 (6.5%) are on Bandits and online learning. They fall into 3 topics.
See NeurIPS 2016 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 · 18 papers
- Efficient Second Order Online Learning by Sketching (50 citations)
- Learning in Games: Robustness of Fast Convergence (44 citations)
- Adaptive Smoothed Online Multi-Task Learning (34 citations)
- MetaGrad: Multiple Learning Rates in Online Learning (20 citations)
- Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning (19 citations)
- Designing smoothing functions for improved worst-case competitive ratio in online optimization (17 citations)
- Coin Betting and Parameter-Free Online Learning (16 citations)
- Regret of Queueing Bandits (15 citations)
- Optimistic Bandit Convex Optimization (14 citations)
- Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities (11 citations)
- Online Convex Optimization with Unconstrained Domains and Losses (11 citations)
- Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions (10 citations)
and 6 more in the interactive map.
Contextual bandits and Thompson sampling · 10 papers
- Fairness in Learning: Classic and Contextual Bandits (191 citations)
- Causal Bandits: Learning Good Interventions via Causal Inference (71 citations)
- Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations (63 citations)
- Linear Contextual Bandits with Knapsacks (60 citations)
- Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Games (52 citations)
- Double Thompson Sampling for Dueling Bandits (40 citations)
- Multiple-Play Bandits in the Position-Based Model (24 citations)
- Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits (13 citations)
- Contextual semibandits via supervised learning oracles (3 citations)
- Regret Bounds for Non-decomposable Metrics with Missing Labels (2 citations)
Multi-armed bandits · 9 papers
- Combinatorial Multi-Armed Bandit with General Reward Functions (75 citations)
- On Explore-Then-Commit strategies (57 citations)
- Refined Lower Bounds for Adversarial Bandits (55 citations)
- Multi-armed Bandits: Competing with Optimal Sequences (31 citations)
- Combinatorial semi-bandit with known covariance (24 citations)
- Threshold Bandits, With and Without Censored Feedback (17 citations)
- Optimistic Gittins Indices (14 citations)
- The Multi-fidelity Multi-armed Bandit (10 citations)
- Verification Based Solution for Structured MAB Problems
