Learning in Repeated Auctions with Budgets: Regret Minimization and Equilibrium

• Published in: Management science Vol. 65; no. 9; pp. 3952 - 3968
• Main Authors: Balseiro, Santiago R., Gur, Yonatan
• Format: Journal Article
• Language: English
• Published: Linthicum INFORMS 01.09.2019; Institute for Operations Research and the Management Sciences
• Subjects: Advertising; Auctions; Bidding; Bids; Budgets; Competition; Competitors; Convergence; dynamic games; Equilibrium; incomplete information; Learning; Markets; Minimization; Online advertising; online learning; Regret; regret analysis; sequential auctions; stochastic approximation; stochastic optimization; Uncertainty; Valuation

In online advertising markets, advertisers often purchase ad placements through bidding in repeated auctions based on realized viewer information. We study how budget-constrained advertisers may compete in such sequential auctions in the presence of uncertainty about future bidding opportunities and...