AAAI 2020 accepted papers on Bandits and online learning
26 of the 1,610 papers accepted at AAAI 2020 (1.6%) are on Bandits and online learning, compared with 1.6% at AAAI 2019. They fall into 3 topics.
See AAAI 2020 in the interactive map
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 · 14 papers
- Efficient Projection-Free Online Methods with Stochastic Recursive Gradient (30 citations)
- Trading-Off Static and Dynamic Regret in Online Least-Squares and Beyond (14 citations)
- Online Second Price Auction with Semi-Bandit Feedback under the Non-Stationary Setting (12 citations)
- Learning to Crawl (10 citations)
- Stochastic Online Learning with Probabilistic Graph Feedback (10 citations)
- Revisiting Online Quantum State Learning (8 citations)
- Optimal Margin Distribution Learning in Dynamic Environments (7 citations)
- Adapting to Smoothness: A More Universal Algorithm for Online Convex Optimization (6 citations)
- Modelling and Solving Online Optimisation Problems (4 citations)
- Distributed Primal-Dual Optimization for Online Multi-Task Learning (3 citations)
- On Adaptivity in Information-Constrained Online Learning (3 citations)
- Path Planning Problems with Side Observations—When Colonels Play Hide-and-Seek (3 citations)
and 2 more in the interactive map.
Contextual bandits and Thompson sampling · 6 papers
- Diversified Interactive Recommendation with Implicit Feedback (79 citations)
- Contextual-Bandit Based Personalized Recommendation with Time-Varying User Interests (39 citations)
- Safe Linear Stochastic Bandits (16 citations)
- Improved Algorithms for Conservative Exploration in Bandits (14 citations)
- Fatigue-Aware Bandits for Dependent Click Models (10 citations)
- Linear Bandits with Feature Feedback (5 citations)
Multi-armed bandits · 6 papers
- Achieving Fairness in the Stochastic Multi-Armed Bandit Problem (70 citations)
- Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack (27 citations)
- A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Bandits (21 citations)
- Incentivized Exploration for Multi-Armed Bandits under Reward Drift (11 citations)
- Observe Before Play: Multi-Armed Bandit with Pre-Observations (11 citations)
- Regret Minimisation in Multi-Armed Bandits Using Bounded Arm Memory (5 citations)
