AAAI 2022 accepted papers on Bandits and online learning
28 of the 1,319 papers accepted at AAAI 2022 (2.1%) are on Bandits and online learning, compared with 2.6% at AAAI 2021. They fall into 4 topics.
See AAAI 2022 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 · 12 papers
- Online Influence Maximization with Node-Level Feedback Using Standard Offline Oracles (15 citations)
- Safe Online Convex Optimization with Unknown Linear Safety Constraints (14 citations)
- Robustification of Online Graph Exploration Methods (13 citations)
- Learning to Identify Top Elo Ratings: A Dueling Bandits Approach (10 citations)
- Learning-Augmented Algorithms for Online Steiner Tree (10 citations)
- A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback (9 citations)
- Real-Time Driver-Request Assignment in Ridesourcing (9 citations)
- Equilibrium Finding in Normal-Form Games via Greedy Regret Minimization (6 citations)
- AutoCFR: Learning to Design Counterfactual Regret Minimization Algorithms (5 citations)
- An Experimental Design Approach for Regret Minimization in Logistic Bandits (3 citations)
- Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model (3 citations)
- Sequential Blocked Matching (2 citations)
Multi-armed bandits · 9 papers
- Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification (10 citations)
- Machine Learning for Online Algorithm Selection under Censored Feedback (6 citations)
- Gaussian Process Bandits with Aggregated Feedback (5 citations)
- Modeling Attrition in Recommender Systems with Departing Bandits (5 citations)
- An Online Learning Approach to Sequential User-Centric Selection Problems (4 citations)
- Learning the Optimal Recommendation from Explorative Users (3 citations)
- A Fast Algorithm for PAC Combinatorial Pure Exploration (1 citation)
- Instance-Sensitive Algorithms for Pure Exploration in Multinomial Logit Bandit (1 citation)
- Max-Min Grouped Bandits (1 citation)
Contextual bandits and Thompson sampling · 4 papers
- Achieving Counterfactual Fairness for Causal Bandit (18 citations)
- A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits (12 citations)
- Context Uncertainty in Contextual Bandits with Applications to Recommender Systems (4 citations)
- Robust Tests in Online Decision-Making (1 citation)
