AAAI 2024 accepted papers on Bandits and online learning
33 of the 2,864 papers accepted at AAAI 2024 (1.2%) are on Bandits and online learning, compared with 1.7% at AAAI 2023. They fall into 4 topics.
See AAAI 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Online convex optimization and games · 11 papers
- Online Submodular Maximization via Online Convex Optimization (5 citations)
- Ahpatron: A New Budgeted Online Kernel Learning Machine with Tighter Mistake Bound (4 citations)
- Dynamic Budget Throttling in Repeated Second-Price Auctions (4 citations)
- Non-stationary Projection-Free Online Learning with Dynamic and Adaptive Regret Guarantees (4 citations)
- Percentile Risk-Constrained Budget Pacing for Guaranteed Display Advertising in Online Optimization (3 citations)
- Cumulative Regret Analysis of the Piyavskii–Shubert Algorithm and Its Variants for Global Optimization (2 citations)
- Improved Bandits in Many-to-One Matching Markets with Incentive Compatibility (2 citations)
- Learning Not to Regret (2 citations)
- Regret Analysis of Repeated Delegated Choice (2 citations)
- Learning-Augmented Online Algorithm for Two-Level Ski-Rental Problem (1 citation)
- No Internal Regret with Non-convex Loss Functions (1 citation)
Contextual bandits and Thompson sampling · 10 papers
- Using Adaptive Bandit Experiments to Increase and Investigate Engagement in Mental Health (11 citations)
- Risk-Aware Continuous Control with Neural Contextual Bandits (4 citations)
- Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach (3 citations)
- Hierarchize Pareto Dominance in Multi-Objective Stochastic Linear Bandits (2 citations)
- New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem (2 citations)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (2 citations)
- Mixed-Effects Contextual Bandits (1 citation)
- Improving Health Information Access in the World’s Largest Maternal Mobile Health Program via Bandit Algorithms
- Responsible Bandit Learning via Privacy-Protected Mean-Volatility Utility
- Contextual Pandora’s Box
Multi-armed bandits · 9 papers
- Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints (7 citations)
- Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit (5 citations)
- Decentralized Scheduling with QoS Constraints: Achieving O(1) QoS Regret of Multi-Player Bandits (4 citations)
- Multiobjective Lipschitz Bandits under Lexicographic Ordering (4 citations)
- Combinatorial Stochastic-Greedy Bandit (3 citations)
- Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits (2 citations)
- Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs (2 citations)
- Eliciting Kemeny Rankings (1 citation)
- Forced Exploration in Bandit Problems (1 citation)
RL theory and MDPs · 3 papers
- Online Markov Decision Processes Configuration with Continuous Decision Space (2 citations)
- Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes (2 citations)
- Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation (1 citation)