Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions

arXiv:2607.02891 · cs.LG, stat.ML · Submitted 2026-07-03 · Read on arXiv

Zihao Hu, Yuan Yao, Jiheng Zhang, Zhengyuan Zhou

cs.LG, stat.ML

Submitted: 2026-07-03

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 62× in this paper · explained in 3 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Contextual Bandits — 3× in this paper · explained in 3 episodes
• Adaptivity — 2× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Non-stationarity — 1× in this paper · explained in 2 episodes

Sources

• Learning to Bid in Non-Stationary Repeated First-Price Auctions
• A Simple Approach for Non-stationary Linear Bandits

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks