Optimal auctions through deep learning

Designing an incentive compatible auction that maximizes expected revenue is an intricate task. The single-item case was resolved in a seminal piece of work by Myerson in 1981. Even after 30-40 years of intense research the problem remains unsolved for seemingly simple multibidder, multi-item settings. In this work, we initiate the exploration of the use of tools from deep learning for the automated design of optimal auctions. We model an auction as a multi-layer neural network, frame optimal auction design as a constrained learning problem, and show how it can be solved using standard pipelines. We prove generalization bounds and present extensive experiments, recovering essentially all known analytical solutions for multi-item settings, and obtaining novel mechanisms for settings in which the optimal mechanism is unknown.

[1]  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.

[2]  Charles A. Wilson,et al.  BUNDLING DECISIONS BY A MULTIPRODUCT MONOPOLIST WITH INCOMPLETE INFORMATION , 2016 .

[3]  Craig Boutilier,et al.  Bidding Languages for Combinatorial Auctions , 2001, IJCAI.

[4]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[5]  Noam Nisan,et al.  The menu-size complexity of auctions , 2013, EC '13.

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

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

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

[9]  Sébastien Lahaie,et al.  A Kernel-Based Iterative Combinatorial Auction , 2011, AAAI.

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

[11]  Paul Dütting,et al.  Machine Learning for Optimal Economic Design , 2019, The Future of Economic Design.

[12]  S. Matthew Weinberg,et al.  Simple Mechanisms for a Subadditive Buyer and Applications to Revenue Monotonicity , 2018, ACM Trans. Economics and Comput..

[13]  Richard G. Baraniuk,et al.  A Probabilistic Framework for Deep Learning , 2016, NIPS.

[14]  Ilya Segal,et al.  Optimal Pricing Mechanisms with Unknown Demand , 2002 .

[15]  Paul R. Milgrom,et al.  Designing Random Allocation Mechanisms: Theory and Applications , 2013 .

[16]  David C. Parkes,et al.  Deep Learning for Revenue-Optimal Auctions with Budgets , 2018, AAMAS.

[17]  Kevin Leyton-Brown,et al.  Deep Learning for Predicting Human Strategic Behavior , 2016, NIPS.

[18]  Mehryar Mohri,et al.  Learning Algorithms for Second-Price Auctions with Reserve , 2016, J. Mach. Learn. Res..

[19]  S. Matthew Weinberg,et al.  Pricing lotteries , 2015, J. Econ. Theory.

[20]  Constantinos Daskalakis,et al.  Multi-item auctions defying intuition? , 2015, SECO.

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

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

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

[24]  Paul Dütting,et al.  Payment Rules through Discriminant-Based Classifiers , 2012, ACM Trans. Economics and Comput..

[25]  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).

[26]  G. Pavlov,et al.  Optimal Mechanism for Selling Two Goods , 2011 .

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

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

[29]  Joseph Sill,et al.  Monotonic Networks , 1997, NIPS.

[30]  David C. Parkes,et al.  A General Statistical Framework for Designing Strategy-proof Assignment Mechanisms , 2016, UAI.

[31]  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.

[32]  John von Neumann,et al.  1. A Certain Zero-sum Two-person Game Equivalent to the Optimal Assignment Problem , 1953 .

[33]  Kevin Leyton-Brown,et al.  Deep IV: A Flexible Approach for Counterfactual Prediction , 2017, ICML.

[34]  J. Rochet.  A necessary and sufficient condition for rationalizability in a quasi-linear context , 1987 .

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

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

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

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

[39]  Maria-Florina Balcan,et al.  Reducing mechanism design to algorithm design via machine learning , 2007, J. Comput. Syst. Sci..

[40]  Pingzhong Tang,et al.  Automated Mechanism Design via Neural Networks , 2018, AAMAS.

[41]  Yann LeCun,et al.  Open Problem: The landscape of the loss surfaces of multilayer networks , 2015, COLT.

[42]  Cynthia Rudin,et al.  Margin-based Ranking and an Equivalence between AdaBoost and RankBoost , 2009, J. Mach. Learn. Res..

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

[44]  Sven Seuken,et al.  Probably Approximately Efficient Combinatorial Auctions via Machine Learning , 2017, AAAI.

[45]  Vincent Conitzer,et al.  Self-interested automated mechanism design and implications for optimal combinatorial auctions , 2004, EC '04.

[46]  Vincent Conitzer,et al.  Complexity of Mechanism Design , 2002, UAI.

[47]  David C. Parkes,et al.  Deep Learning for Multi-Facility Location Mechanism Design , 2018, IJCAI.

[48]  Vincent Conitzer,et al.  Mechanism Design with Unknown Correlated Distributions: Can We Learn Optimal Mechanisms? , 2017, AAMAS.

[49]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[51]  Elias Koutsoupias,et al.  Selling Two Goods Optimally , 2015, ICALP.

[52]  T. Sandholm,et al.  Applications of Automated Mechanism Design , 2003 .

[53]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[54]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[56]  Andrew Chi-Chih Yao,et al.  On revenue maximization for selling multiple independently distributed items , 2013, Proceedings of the National Academy of Sciences.

[57]  Max Welling,et al.  Causal Effect Inference with Deep Latent-Variable Models , 2017, NIPS 2017.

[58]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .

[59]  Drew Fudenberg,et al.  Predicting and Understanding Initial Play , 2019, American Economic Review.

[60]  Shuchi Chawla,et al.  Bayesian algorithmic mechanism design , 2014, SECO.

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

[62]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

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

[64]  Kenji Kawaguchi,et al.  Deep Learning without Poor Local Minima , 2016, NIPS.

[65]  Christos Tzamos,et al.  Strong Duality for a Multiple-Good Monopolist , 2014, EC.

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

[67]  Nima Haghpanah,et al.  When Is Pure Bundling Optimal? , 2020 .

[68]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[69]  Philippe Jehiel,et al.  Mixed Bundling Auctions , 2006, J. Econ. Theory.

[70]  Daniel Soudry,et al.  No bad local minima: Data independent training error guarantees for multilayer neural networks , 2016, ArXiv.

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

[72]  Yang Cai,et al.  Understanding Incentives: Mechanism Design Becomes Algorithm Design , 2013, 2013 IEEE 54th Annual Symposium on Foundations of Computer Science.

[73]  Kamesh Munagala,et al.  Optimal auctions via the multiplicative weight method , 2012, EC '13.

[74]  Pingzhong Tang,et al.  Computer-aided mechanism design: designing revenue-optimal mechanisms via neural networks , 2018, ArXiv.

[75]  Jacob Andreas,et al.  Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? , 2017, ICML.

[76]  Claudio Gentile,et al.  Ieee Transactions on Information Theory 1 Regret Minimization for Reserve Prices in Second-price Auctions , 2022 .

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

[78]  Shuchi Chawla,et al.  Mechanism design for data science , 2014, EC.

[79]  David C. Parkes,et al.  Automated Mechanism Design without Money via Machine Learning , 2016, IJCAI.

[80]  R. Vohra,et al.  Market Research and Market Design , 2003 .

[81]  Mehryar Mohri,et al.  Learning Theory and Algorithms for revenue optimization in second price auctions with reserve , 2013, ICML.

[82]  Andrew Chi-Chih Yao.  On Solutions for the Maximum Revenue Multi-item Auction under Dominant-Strategy and Bayesian Implementations , 2016, ArXiv.

[83]  Kevin Waugh,et al.  DeepStack: Expert-level artificial intelligence in heads-up no-limit poker , 2017, Science.

[84]  Nikhil R. Devanur,et al.  Revenue Maximization and Ex-Post Budget Constraints , 2015, EC.

[85]  Thore Graepel,et al.  A Neural Architecture for Designing Truthful and Efficient Auctions , 2019, ArXiv.

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

[87]  Pingzhong Tang,et al.  Reinforcement mechanism design , 2017, IJCAI.

[88]  Dimitri P. Bertsekas,et al.  Constrained Optimization and Lagrange Multiplier Methods , 1982 .

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

[90]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

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

[92]  Tuomas Sandholm,et al.  Automated Design of Revenue-Maximizing Combinatorial Auctions , 2015, Oper. Res..

[93]  Kevin Leyton-Brown,et al.  The Positronic Economist: A Computational System for Analyzing Economic Mechanisms , 2017, AAAI.

[94]  Vincent Conitzer,et al.  Computationally Feasible Automated Mechanism Design: General Approach and Case Studies , 2010, AAAI.

[95]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[96]  Elias Koutsoupias,et al.  Duality and optimality of auctions for uniform distributions , 2014, SIAM J. Comput..

[97]  Nima Haghpanah,et al.  Multi-dimensional Virtual Values and Second-degree Price Discrimination , 2014 .

[98]  Jason D. Hartline.  Bayesian Mechanism Design , 2013, Found. Trends Theor. Comput. Sci..