Learning in Repeated Auctions with Budgets: Regret Minimization and Equilibrium
Top Cited Papers
- 1 September 2019
- journal article
- research article
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 65 (9) , 3952-3968
Abstract
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 competition. We formulate this problem as a sequential game of incomplete information, in which bidders know neither their own valuation distribution nor the budgets and valuation distributions of their competitors. We introduce a family of practical bidding strategies we refer to as adaptive pacing strategies, in which advertisers adjust their bids according to the sample path of expenditures they exhibit, and analyze the performance of these strategies in different competitive settings. We establish the asymptotic optimality of these strategies when competitors’ bids are independent and identically distributed over auctions, but also when competing bids are arbitrary. When all the bidders adopt these strategies, we establish the convergence of the induced dynamics and characterize a regime (well motivated in the context of online advertising markets) under which these strategies constitute an approximate Nash equilibrium in dynamic strategies: the benefit from unilaterally deviating to other strategies, including ones with access to complete information, becomes negligible as the number of auctions and competitors grows large. This establishes a connection between regret minimization and market stability, by which advertisers can essentially follow approximate equilibrium bidding strategies that also ensure the best performance that can be guaranteed off equilibrium. This paper was accepted by Noah Gans, stochastic models and simulation.Keywords
This publication has 31 references indexed in Scilit:
- Budget Management Strategies in Repeated Auctions2017
- Non-Stationary Stochastic OptimizationOperations Research, 2015
- Repeated Auctions with Budgets in Ad Exchanges: Approximations and DesignManagement Science, 2015
- Yield Optimization of Display Advertising with Ad ExchangeManagement Science, 2014
- Bandits with Knapsacks2013
- Revenue Management with Incomplete Demand Information2011
- Dynamics of bid optimization in online advertisement auctions2007
- Efficient learning equilibriumArtificial Intelligence, 2004
- Mirror descent and nonlinear projected subgradient methods for convex optimizationOperations Research Letters, 2003
- Adaptive Algorithms and Stochastic Approximations1990