AI RESEARCH
Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions
arXiv CS.LG
•
ArXi:2605.09448v1 Announce Type: new The transition to First-Price Auctions (FPA) in digital advertising has spurred significant research, yet existing work typically assumes access to a valuation oracle, ignoring the reality that values must be inferred from censored data. While Linear Treatment Effect (LTE) models address this by learning value uplift, they have not been adapted to realistic settings with hard Budget constraints or Return-on-Spend (RoS) targets requiring regret and violation control.