2 papers
cs.LG2026
Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions
Zihao Hu, Yuan Yao, Jiheng Zhang +1
Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can…
cs.LG2025
Learning to Bid in Non-Stationary Repeated First-Price Auctions
Zihao Hu, Xiaoyu Fan, Yuan Yao +2
First-price auctions have recently gained significant traction in digital advertising markets, exemplified by Google's transition from second-price to first-price auctions. Unlike…