The Sample Complexity of Up-to-ε Multi-Dimensional Revenue Maximization

We consider the sample complexity of revenue maximization for multiple bidders in unrestricted multi-dimensional settings. Specifically, we study the standard model of $n$ additive bidders whose values for $m$ heterogeneous items are drawn independently. For any such instance and any $\varepsilon>0$, we show that it is possible to learn an $\varepsilon$-Bayesian Incentive Compatible auction whose expected revenue is within $\varepsilon$ of the optimal $\varepsilon$-BIC auction from only polynomially many samples. Our fully nonparametric approach is based on ideas that hold quite generally, and completely sidestep the difficulty of characterizing optimal (or near-optimal) auctions for these settings. Therefore, our results easily extend to general multi-dimensional settings, including valuations that aren't necessarily even subadditive, and arbitrary allocation constraints. For the cases of a single bidder and many goods, or a single parameter (good) and many bidders, our analysis yields exact incentive compatibility (and for the latter also computational efficiency). Although the single-parameter case is already well-understood, our corollary for this case extends slightly the state-of-the-art.

[1]  Shaddin Dughmi,et al.  Bernoulli factories and black-box reductions in mechanism design , 2017, SECO.

[2]  S. Matthew Weinberg,et al.  Simple Mechanisms for a Combinatorial Buyer and Applications to Revenue Monotonicity , 2015, ArXiv.

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

[4]  Edith Elkind,et al.  Designing and learning optimal finite support auctions , 2007, SODA '07.

[5]  Yakov Babichenko,et al.  Empirical Distribution of Equilibrium Play and Its Testing Application , 2013, Math. Oper. Res..

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

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

[8]  Christos Tzamos,et al.  The Complexity of Black-Box Mechanism Design with Priors , 2019, EC.

[9]  Shuchi Chawla,et al.  Mechanism Design for Subadditive Agents via an Ex Ante Relaxation , 2016, EC.

[10]  Yannai A. Gonczarowski Bounding the menu-size of approximately optimal auctions via optimal-transport duality , 2017, STOC.

[11]  Jason D. Hartline,et al.  Sample Complexity for Non-Truthful Mechanisms , 2016, EC.

[12]  Robert D. Kleinberg,et al.  Bayesian incentive compatibility via matchings , 2011, SODA '11.

[13]  Moshe Babaioff,et al.  The menu-size complexity of revenue approximation , 2016, STOC.

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

[15]  Christos Tzamos,et al.  Mechanism design via optimal transport , 2013, EC '13.

[16]  Yang Cai,et al.  Simple mechanisms for subadditive buyers via duality , 2016, STOC.

[17]  S. Matthew Weinberg,et al.  A Simple and Approximately Optimal Mechanism for an Additive Buyer , 2014, 2014 IEEE 55th Annual Symposium on Foundations of Computer Science.

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

[19]  Nikhil R. Devanur,et al.  A Duality-Based Unified Approach to Bayesian Mechanism Design , 2019, SIAM J. Comput..

[20]  Jason D. Hartline,et al.  Non-Revelation Mechanism Design , 2016, ArXiv.

[21]  Xiaohui Bei,et al.  Bayesian incentive compatibility via fractional assignments , 2010, SODA '11.

[22]  S. Hart,et al.  Maximal revenue with multiple goods: Nonmonotonicity and other observations , 2015 .

[23]  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.

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

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

[26]  Tim Roughgarden,et al.  Revenue maximization with a single sample , 2010, EC '10.

[27]  S. Weinberg,et al.  Approximation Schemes for a Buyer with Independent Items via Symmetries , 2019, ArXiv.

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

[29]  Chenghao Guo,et al.  Generalizing Complex Hypotheses on Product Distributions: Auctions, Prophet Inequalities, and Pandora's Problem , 2019, COLT.

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

[31]  Nir Shabbat Approximate Revenue Maximization with Multiple Items , 2012 .

[32]  Andrew Chi-Chih Yao,et al.  An n-to-1 Bidder Reduction for Multi-item Auctions and its Applications , 2014, SODA.

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

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

[35]  Andrew Chi-Chih Yao,et al.  Dominant-Strategy versus Bayesian Multi-item Auctions: Maximum Revenue Determination and Comparison , 2017, EC.

[36]  Vasilis Syrgkanis A Sample Complexity Measure with Applications to Learning Optimal Auctions , 2017, NIPS.

[37]  Yang Cai,et al.  Learning Multi-Item Auctions with (or without) Samples , 2017, 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS).

[38]  Tim Roughgarden,et al.  Making the Most of Your Samples , 2018, SIAM J. Comput..

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

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

[41]  S. Matthew Weinberg,et al.  The Sample Complexity of Up-to-ε Multi-Dimensional Revenue Maximization , 2018, 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS).

[42]  Noam Nisan,et al.  Sampling and Representation Complexity of Revenue Maximization , 2014, WINE.

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

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

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