Deep Contract Design via Discontinuous Piecewise Affine Neural Networks

Contract design involves a principal who establishes contractual agreements about payments for outcomes that arise from the actions of an agent. In this paper, we initiate the study of deep learning for the automated design of optimal contracts. We formulate this as an offline learning problem, where a deep network is used to represent the principal's expected utility as a function of the design of a contract. We introduce a novel representation: the Discontinuous ReLU (DeLU) network, which models the principal's utility as a discontinuous piecewise affine function where each piece corresponds to the agent taking a particular action. DeLU networks implicitly learn closed-form expressions for the incentive compatibility constraints of the agent and the utility maximization objective of the principal, and support parallel inference on each piece through linear programming or interior-point methods that solve for optimal contracts. We provide empirical results that demonstrate success in approximating the principal's utility function with a small number of training samples and scaling to find approximately optimal contracts on problems with a large number of actions and outcomes.

[1]  Paul Dütting,et al.  Bayesian Analysis of Linear Contracts , 2022, EC.

[2]  Michael I. Jordan,et al.  The Sample Complexity of Online Contract Design , 2022, EC.

[3]  M. Feldman,et al.  Multi-agent Contracts , 2022, STOC.

[4]  Dylan Hadfield-Menell,et al.  Get It in Writing: Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL , 2022, AAMAS.

[5]  N. Gatti,et al.  Designing Menus of Contracts Efficiently: The Power of Randomization , 2022, EC.

[6]  Alexander R. Trott,et al.  Solving Dynamic Principal-Agent Problems with a Rationally Inattentive Principal , 2022, ArXiv.

[7]  Michal Feldman,et al.  Combinatorial Contracts , 2021, 2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS).

[8]  Nicola Gatti,et al.  Bayesian Agency: Linear versus Tractable Contracts , 2021, EC.

[9]  MANISH RAGHAVAN,et al.  Algorithmic classification and strategic effort , 2020, SIGecom Exch..

[10]  Jon Schneider,et al.  Contracts under Moral Hazard and Adverse Selection , 2020, EC.

[11]  Inbal Talgam-Cohen,et al.  Multiagent Evaluation Mechanisms , 2020, AAAI.

[12]  Tim Roughgarden,et al.  The Complexity of Contracts , 2020, SODA.

[13]  Gabriel Carroll,et al.  Robustness in Mechanism Design and Contracting , 2019, Annual Review of Economics.

[14]  Alon Cohen,et al.  Learning Approximately Optimal Contracts , 2018, SAGT.

[15]  Matthias Hein,et al.  Provable Robustness of ReLU networks via Maximization of Linear Regions , 2018, AISTATS.

[16]  Matthias Hein,et al.  A randomized gradient-free attack on ReLU networks , 2018, GCPR.

[17]  Tim Roughgarden,et al.  Simple versus Optimal Contracts , 2018, EC.

[18]  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).

[19]  Jon M. Kleinberg,et al.  How Do Classifiers Induce Agents to Invest Effort Strategically? , 2018, EC.

[20]  Abien Fred Agarap.  Deep Learning using Rectified Linear Units (ReLU) , 2018, ArXiv.

[21]  Jian Pei,et al.  Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution , 2018, KDD.

[22]  Yannai A. Gonczarowski.  Bounds on the Menu-Size of Approximately Optimal Auctions via Optimal-Transport Duality , 2017, ArXiv.

[23]  Paul Dütting,et al.  Optimal auctions through deep learning , 2017, ICML.

[24]  D. Parkes,et al.  Optimal Auctions through Deep Learning: Advances in Differentiable Economics , 2017, 1706.03459.

[25]  Raman Arora,et al.  Understanding Deep Neural Networks with Rectified Linear Units , 2016, Electron. Colloquium Comput. Complex..

[26]  Nikhil R. Devanur,et al.  A duality based unified approach to Bayesian mechanism design , 2016, STOC.

[27]  Nikhil R. Devanur,et al.  A duality based unified approach to Bayesian mechanism design , 2016, Symposium on the Theory of Computing.

[28]  Li Han,et al.  Mixture Selection, Mechanism Design, and Signaling , 2015, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[29]  Tilman Börgers,et al.  An introduction to the theory of mechanism design , 2015 .

[30]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[31]  Haifeng Xu,et al.  Algorithmic Bayesian persuasion , 2015, STOC.

[32]  Gabriel D. Carroll.  Robustness and Linear Contracts , 2015 .

[33]  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.

[34]  Aleksandrs Slivkins,et al.  Adaptive contract design for crowdsourcing markets: bandit algorithms for repeated principal-agent problems , 2014, J. Artif. Intell. Res..

[35]  Shaddin Dughmi,et al.  On the Hardness of Signaling , 2014, 2014 IEEE 55th Annual Symposium on Foundations of Computer Science.

[36]  Luciano Messori.  The Theory of Incentives I: The Principal-Agent Model , 2013 .

[37]  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.

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

[39]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[40]  Emir Kamenica,et al.  Bayesian Persuasion , 2009 .

[41]  Moshe Babaioff,et al.  Combinatorial agency , 2006, EC '06.

[42]  Stephen J. Wright.  On the convergence of the Newton/log-barrier method , 2001, Math. Program..

[43]  Bernard Salanié,et al.  The Economics of Contracts: A Primer , 1997 .

[44]  Joshua R. Wang,et al.  Optimal No-Regret Learning for One-Sided Lipschitz Functions , 2023, ICML.

[45]  Iain Dunning,et al.  PuLP : A Linear Programming Toolkit for Python , 2011 .

[46]  A. Young.  Contract Theory , 2011 .

[47]  Stephen J. Wright,et al.  Primal-Dual Interior-Point Methods , 1997 .