Are Two (Samples) Really Better Than One?

The literature on "mechanism design from samples," which has flourished in recent years at the interface of economics and computer science, offers a bridge between the classic computer-science approach of worst-case analysis (corresponding to "no samples") and the classic economic approach of average-case analysis for a given Bayesian prior (conceptually corresponding to the number of samples tending to infinity). Nonetheless, the two directions studied so far are two extreme and almost diametrically opposed directions: that of asymptotic results where the number of samples grows large, and that where only a single sample is available. In this paper, we take a first step toward understanding the middle ground that bridges these two approaches: that of a fixed number of samples greater than one. In a variety of contexts, we ask what is possibly the most fundamental question in this direction: are two samples really better than one sample?. We present a few surprising negative results, and complement them with our main result: showing that the worst-case, over all regular distributions, expected-revenue guarantee of the Empirical Revenue Maximization algorithm given two samples is greater than that of this algorithm given one sample. The proof is technically challenging, and provides the first result that shows that some deterministic mechanism constructed using two samples can guarantee more than one half of the optimal revenue.

[1]  Tim Roughgarden,et al.  Revenue maximization with a single sample , 2015, Games Econ. Behav..

[2]  Tim Roughgarden,et al.  Ironing in the Dark , 2015, EC.

[3]  Maria-Florina Balcan,et al.  A General Theory of Sample Complexity for Multi-Item Profit Maximization , 2017, EC.

[4]  Claudio Gentile,et al.  Regret Minimization for Reserve Prices in Second-Price Auctions , 2013, IEEE Transactions on Information Theory.

[5]  Noga Alon,et al.  Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues , 2017, NIPS.

[6]  Tim Roughgarden,et al.  Learning Simple Auctions , 2016, COLT.

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

[8]  Maria-Florina Balcan,et al.  Sample Complexity of Automated Mechanism Design , 2016, NIPS.

[9]  Yoav Shoham,et al.  Truth revelation in approximately efficient combinatorial auctions , 2002, EC '99.

[10]  Richard Cole,et al.  The sample complexity of revenue maximization , 2014, STOC.

[11]  Maria-Florina Balcan,et al.  Sample Complexity of Multi-Item Profit Maximization , 2017, ArXiv.

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

[13]  Jason D. Hartline.  Mechanism Design and Approximation , 2014 .

[14]  Nikhil R. Devanur,et al.  The sample complexity of auctions with side information , 2015, STOC.

[15]  Tim Roughgarden,et al.  Making the Most of Your Samples , 2014, EC.

[16]  Silvio Micali,et al.  Parametric digital auctions , 2013, ITCS '13.

[17]  Tim Roughgarden,et al.  Simple versus optimal mechanisms , 2009, EC '09.

[18]  Nicole Immorlica,et al.  Randomization Beats Second Price as a Prior-Independent Auction , 2015, EC.

[19]  Jeremy I. Bulow,et al.  Auctions versus Negotiations , 1996 .

[20]  Yannai A. Gonczarowski,et al.  Efficient empirical revenue maximization in single-parameter auction environments , 2016, STOC.

[21]  Tim Roughgarden,et al.  On the Pseudo-Dimension of Nearly Optimal Auctions , 2015, NIPS.

[22]  Andrew V. Goldberg,et al.  Competitive auctions and digital goods , 2001, SODA '01.