Sampling and Representation Complexity of Revenue Maximization

We consider (approximate) revenue maximization in mechanisms where the distribution on input valuations is given via “black box” access to samples from the distribution. We analyze the following model: a single agent, m outcomes, and valuations represented as m-dimensional vectors indexed by the outcomes and drawn from an arbitrary distribution presented as a black box. We observe that the number of samples required – the sample complexity – is tightly related to the representation complexity of an approximately revenue-maximizing auction. Our main results are upper bounds and an exponential lower bound on these complexities. We also observe that the computational task of “learning” a good mechanism from a sample is nontrivial, requiring careful use of regularization in order to avoid over-fitting the mechanism to the sample. We establish preliminary positive and negative results pertaining to the computational complexity of learning a good mechanism for the original distribution by operating on a sample from said distribution.

[1]  Shuchi Chawla,et al.  Multi-parameter mechanism design and sequential posted pricing , 2010, BQGT.

[2]  Saeed Alaei,et al.  Bayesian Combinatorial Auctions: Expanding Single Buyer Mechanisms to Many Buyers , 2011, 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science.

[3]  Jason D. Hartline,et al.  Multi-parameter mechanism design and sequential posted pricing , 2009, STOC '10.

[4]  Nima Haghpanah,et al.  Bayesian optimal auctions via multi- to single-agent reduction , 2012, EC '12.

[5]  Yang Cai,et al.  Simple and Nearly Optimal Multi-Item Auctions , 2012, SODA.

[6]  Vladlen Koltun,et al.  Near-Optimal Pricing in Near-Linear Time , 2005, WADS.

[7]  Roger B. Myerson,et al.  Optimal Auction Design , 1981, Math. Oper. Res..

[8]  R. McAfee,et al.  Multidimensional incentive compatibility and mechanism design , 1988 .

[9]  Yang Cai,et al.  Optimal Multi-dimensional Mechanism Design: Reducing Revenue to Welfare Maximization , 2012, 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science.

[10]  John Thanassoulis,et al.  Haggling over substitutes , 2004, J. Econ. Theory.

[11]  Nima Haghpanah,et al.  Mechanism Design via Multi- to Single-agent Reduction , 2012, EC 2012.

[12]  Shuchi Chawla,et al.  Algorithmic pricing via virtual valuations , 2007, EC '07.

[13]  Maria-Florina Balcan,et al.  Mechanism design via machine learning , 2005, 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05).

[14]  S. Matthew Weinberg,et al.  Symmetries and optimal multi-dimensional mechanism design , 2012, EC '12.

[15]  Noam Nisan,et al.  The menu-size complexity of auctions , 2013, EC.

[16]  Shuchi Chawla,et al.  The power of randomness in bayesian optimal mechanism design , 2010, EC '10.

[17]  S. Matthew Weinberg,et al.  Pricing randomized allocations , 2009, SODA '10.

[18]  Alejandro M. Manelli,et al.  Bundling as an optimal selling mechanism for a multiple-good monopolist , 2006, J. Econ. Theory.

[19]  Yang Cai,et al.  Extreme-Value Theorems for Optimal Multidimensional Pricing , 2011, 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science.

[20]  Yang Cai,et al.  An algorithmic characterization of multi-dimensional mechanisms , 2011, STOC '12.