AAAI 2021 accepted papers on Bandits and online learning
43 of the 1,654 papers accepted at AAAI 2021 (2.6%) are on Bandits and online learning, compared with 1.6% at AAAI 2020. They fall into 4 topics.
See AAAI 2021 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 · 15 papers
- Online Optimal Control with Affine Constraints (24 citations)
- Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent (23 citations)
- Data-driven Competitive Algorithms for Online Knapsack and Set Cover (20 citations)
- Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions (17 citations)
- On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems (15 citations)
- Projection-free Online Learning over Strongly Convex Sets (11 citations)
- Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games (8 citations)
- Projection-free Online Learning in Dynamic Environments (8 citations)
- Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games (7 citations)
- Competitive Analysis for Two-Level Ski-Rental Problem (5 citations)
- Online DR-Submodular Maximization: Minimizing Regret and Constraint Violation (5 citations)
- Policy Optimization as Online Learning with Mediator Feedback (4 citations)
and 3 more in the interactive map.
Contextual bandits and Thompson sampling · 13 papers
- A Hybrid Bandit Framework for Diversified Recommendation (23 citations)
- Multinomial Logit Contextual Bandits: Provable Optimality and Practicality (16 citations)
- Learning from eXtreme Bandit Feedback (11 citations)
- Relational Boosted Bandits (7 citations)
- Robust Bandit Learning with Imperfect Context (6 citations)
- Decentralized Multi-Agent Linear Bandits with Safety Constraints (5 citations)
- Adversarial Linear Contextual Bandits with Graph-Structured Side Observations (4 citations)
- Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits (4 citations)
- Disposable Linear Bandits for Online Recommendations (3 citations)
- Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions (2 citations)
- Robust Contextual Bandits via Bootstrapping (1 citation)
- A Bayesian Approach for Subset Selection in Contextual Bandits
and 1 more in the interactive map.
Multi-armed bandits · 12 papers
- Federated Multi-Armed Bandits (64 citations)
- Regret Bounds for Batched Bandits (23 citations)
- Quantum Exploration Algorithms for Multi-Armed Bandits (18 citations)
- Combinatorial Pure Exploration with Full-Bandit or Partial Linear Feedback (10 citations)
- Adaptive Algorithms for Multi-armed Bandit with Composite and Anonymous Feedback (7 citations)
- Stochastic Bandits with Graph Feedback in Non-Stationary Environments (6 citations)
- DART: Adaptive Accept Reject Algorithm for Non-Linear Combinatorial Bandits (5 citations)
- Stochastic Graphical Bandits with Adversarial Corruptions (4 citations)
- A One-Size-Fits-All Solution to Conservative Bandit Problems (2 citations)
- Lenient Regret for Multi-Armed Bandits (2 citations)
- Near-Optimal MNL Bandits Under Risk Criteria (2 citations)
- Robustness Guarantees for Mode Estimation with an Application to Bandits (1 citation)
