No-Regret Learning in Partially-Informed Auctions

Auctions with partially-revealed information about items are broadly employed in real-world applications, but the underlying mechanisms have limited theoretical support. In this work, we study a machine learning formulation of these types of mechanisms, presenting algorithms that are no-regret from the buyer’s perspective. Specifically, a buyer who wishes to maximize his utility interacts repeatedly with a platform over a series of T rounds. In each round, a new item is drawn from an unknown distribution and the platform publishes a price together with incomplete, “masked” information about the item. The buyer then decides whether to purchase the item. We formalize this problem as an online learning task where the goal is to have low regret with respect to a myopic oracle that has perfect knowledge of the distribution over items and the seller’s masking function. When the distribution over items is known to the buyer and the mask is a SimHash function mapping R d to { 0 , 1 } ℓ , our algorithm has regret ˜ O (( T dℓ ) 1 / 2 ) . In a fully agnostic setting when the mask is an arbitrary function mapping to a set of size n and the prices are stochastic, our algorithm has regret ˜ O (( T n ) 1 / 2 ) .

[1]  Sergei Vassilvitskii,et al.  Clustering for Private Interest-based Advertising , 2021, KDD.

[2]  Revealing information in auctions: The optimal auction versus the second-price auction , 2021, Economics Letters.

[3]  Hema Yoganarasimhan,et al.  Targeting and Privacy in Mobile Advertising , 2020, Mark. Sci..

[4]  D. Bergemann,et al.  Selling Impressions: Efficiency vs. Competition , 2021 .

[5]  Aleksandrs Slivkins,et al.  Introduction to Multi-Armed Bandits , 2019, Found. Trends Mach. Learn..

[6]  Vasilis Syrgkanis,et al.  Learning to Bid Without Knowing your Value , 2017, EC.

[7]  Balázs Szentes,et al.  Buyer-Optimal Learning and Monopoly Pricing , 2017 .

[8]  Yonatan Gur,et al.  Learning in Repeated Auctions with Budgets: Regret Minimization and Equilibrium , 2017, EC.

[9]  Hao Li,et al.  Discriminatory Information Disclosure , 2017 .

[10]  Daniel Z. Li,et al.  Cheap Talk Advertising in Auctions: Horizontally vs Vertically Differentiated Products , 2017 .

[11]  Vianney Perchet,et al.  Online learning in repeated auctions , 2015, COLT.

[12]  Paul Milgrom,et al.  Adverse Selection and Auction Design for Internet Display Advertising , 2015, EAI Endorsed Trans. Scalable Inf. Syst..

[13]  Alexandre de Corniere,et al.  Online Advertising and Privacy , 2014 .

[14]  J. Wellner,et al.  Log-Concavity and Strong Log-Concavity: a review. , 2014, Statistics surveys.

[15]  Éva Tardos,et al.  Can Credit Increase Revenue? , 2013, WINE.

[16]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[17]  Saikat Guha,et al.  Privad: Practical Privacy in Online Advertising , 2011, NSDI.

[18]  John Langford,et al.  Contextual Bandit Algorithms with Supervised Learning Guarantees , 2010, AISTATS.

[19]  Paul Milgrom,et al.  Simplified mechanisms with an application to sponsored-search auctions , 2010, Games Econ. Behav..

[20]  Alex Gershkov,et al.  Optimal auctions and information disclosure , 2009 .

[21]  Péter Eso,et al.  Optimal Information Disclosure in Auctions and the Handicap Auction , 2007 .

[22]  Dirk Bergemann,et al.  Information Structures in Optimal Auctions , 2001, J. Econ. Theory.

[23]  Santosh S. Vempala,et al.  Fast Algorithms for Logconcave Functions: Sampling, Rounding, Integration and Optimization , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

[24]  Paul Milgrom,et al.  Putting Auction Theory to Work , 2004 .

[25]  M. Bagnoli,et al.  Log-concave probability and its applications , 2004 .

[26]  J. Ganuza,et al.  Ignorance Promotes Competition: An Auction Model with Endogenous Private Valuations , 2003 .

[27]  Ari Juels,et al.  Targeted Advertising ... And Privacy Too , 2001, CT-RSA.

[28]  Peter L. Bartlett,et al.  Neural Network Learning - Theoretical Foundations , 1999 .

[29]  G. Sheblé,et al.  Application of auctions as a pricing mechanism for the interchange of electric power , 1995 .

[30]  David Haussler,et al.  Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..