NeurIPS 2018 accepted papers on Bandits and online learning
43 of the 1,008 papers accepted at NeurIPS 2018 (4.3%) are on Bandits and online learning, compared with 6.1% at NeurIPS 2017. They fall into 4 topics.
See NeurIPS 2018 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 · 20 papers
- Online convex optimization for cumulative constraints (72 citations)
- Adaptive Online Learning in Dynamic Environments (70 citations)
- Generalized Inverse Optimization through Online Learning (33 citations)
- Contextual Pricing for Lipschitz Buyers (30 citations)
- Bandit Learning in Concave N-Person Games (28 citations)
- Online Learning of Quantum States (22 citations)
- Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator (19 citations)
- Efficient Online Portfolio with Logarithmic Regret (16 citations)
- Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models (13 citations)
- Online Improper Learning with an Approximation Oracle (12 citations)
- Multiplicative Weights Updates with Constant Step-Size in Graphical Constant-Sum Games (7 citations)
- Horizon-Independent Minimax Linear Regression (5 citations)
and 8 more in the interactive map.
Contextual bandits and Thompson sampling · 11 papers
- Online Learning with an Unknown Fairness Metric (78 citations)
- Differentially Private Contextual Linear Bandits (51 citations)
- TopRank: A practical algorithm for online stochastic ranking (33 citations)
- An Information-Theoretic Analysis for Thompson Sampling with Many Actions (24 citations)
- Fighting Boredom in Recommender Systems with Linear Reinforcement Learning (20 citations)
- Bandit Learning with Implicit Feedback (15 citations)
- PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits (10 citations)
- Contextual bandits with surrogate losses: Margin bounds and efficient algorithms (9 citations)
- A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem (6 citations)
- Factored Bandits (6 citations)
- Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior (4 citations)
Multi-armed bandits · 10 papers
- Adversarial Attacks on Stochastic Bandits (48 citations)
- Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs (17 citations)
- Multi-armed Bandits with Compensation (14 citations)
- A Bandit Approach to Sequential Experimental Design with False Discovery Control (11 citations)
- Distributed Multi-Player Bandits - a Game of Thrones Approach (11 citations)
- Bandit Learning with Positive Externalities (9 citations)
- Coordinate Descent with Bandit Sampling (7 citations)
- Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task (3 citations)
- Adaptive Learning with Unknown Information Flows (1 citation)
- Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward
