JMLR 2023 papers on Bandits and online learning
15 of the 354 papers published in JMLR 2023 (4.2%) are on Bandits and online learning, compared with 2.8% at JMLR 2022. They fall into 3 topics.
See JMLR 2023 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 · 7 papers
- Non-stationary Online Learning with Memory and Non-stochastic Control (14 citations)
- Robust Load Balancing with Machine Learned Advice (8 citations)
- Finite-time Koopman Identifier: A Unified Batch-online Learning Framework for Joint Learning of Koopman Structure and Parameters (3 citations)
- A PDE approach for regret bounds under partial monitoring (2 citations)
- Linear Partial Monitoring for Sequential Decision Making: Algorithms, Regret Bounds and Applications
- Online Non-stochastic Control with Partial Feedback
- Online Optimization over Riemannian Manifolds
Multi-armed bandits · 6 papers
- A New Look at Dynamic Regret for Non-Stationary Stochastic Bandits (15 citations)
- Bandit problems with fidelity rewards (1 citation)
- Adaptive Data Depth via Multi-Armed Bandits
- Continuous-in-time Limit for Bayesian Bandits
- Adaptation to the Range in K-Armed Bandits
- VCG Mechanism Design with Unknown Agent Values under Stochastic Bandit Feedback
