The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations
This work addresses the challenge of learning optimal bidding strategies in auctions for bidders and auction designers, but it is incremental as it builds on existing regret minimization frameworks.
The paper tackles the problem of minimizing regret for a bidder in repeated first-price auctions where item values are unknown until winning, by characterizing minimax regret in terms of auction transparency and environmental assumptions. The result provides a complete characterization up to logarithmic factors, showing how transparency and environment type affect learning speed for optimal bidding.
We study the problem of regret minimization for a single bidder in a sequence of first-price auctions where the bidder discovers the item's value only if the auction is won. Our main contribution is a complete characterization, up to logarithmic factors, of the minimax regret in terms of the auction's \emph{transparency}, which controls the amount of information on competing bids disclosed by the auctioneer at the end of each auction. Our results hold under different assumptions (stochastic, adversarial, and their smoothed variants) on the environment generating the bidder's valuations and competing bids. These minimax rates reveal how the interplay between transparency and the nature of the environment affects how fast one can learn to bid optimally in first-price auctions.