Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function

Computing Nash equilibrium (NE) of multi-player games has witnessed renewed interest due to recent advances in generative adversarial networks. However, computing equilibrium efficiently is challenging. To this end, we introduce the Gradient-based Nikaido-Isoda (GNI) function which serves: (i) as a merit function, vanishing only at the first-order stationary points of each player's optimization problem, and (ii) provides error bounds to a stationary Nash point. Gradient descent is shown to converge sublinearly to a first-order stationary point of the GNI function. For the particular case of bilinear min-max games and multi-player quadratic games, the GNI function is convex. Hence, the application of gradient descent in this case yields linear convergence to an NE (when one exists). In our numerical experiments, we observe that the GNI formulation always converges to the first-order stationary point of each player's optimization problem.

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

[2]  J. Zico Kolter,et al.  Gradient descent GAN optimization is locally stable , 2017, NIPS.

[3]  G. M. Korpelevich The extragradient method for finding saddle points and other problems , 1976 .

[4]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Francisco Facchinei,et al.  Penalty Methods for the Solution of Generalized Nash Equilibrium Problems , 2010, SIAM J. Optim..

[7]  Constantinos Daskalakis,et al.  Training GANs with Optimism , 2017, ICLR.

[8]  Constantinos Daskalakis,et al.  The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization , 2018, NeurIPS.

[9]  Francisco Facchinei,et al.  Generalized Nash Equilibrium Problems , 2010, Ann. Oper. Res..

[10]  J. Krawczyk,et al.  Numerical solutions to Nash-Cournot equilibria in coupled constraint electricity markets , 2004, IEEE Transactions on Power Systems.

[11]  T. Başar,et al.  Dynamic Noncooperative Game Theory , 1982 .

[12]  Christian Kanzow,et al.  Optimization reformulations of the generalized Nash equilibrium problem using Nikaido-Isoda-type functions , 2009, Comput. Optim. Appl..

[13]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[14]  H. Nikaidô,et al.  Note on non-cooperative convex game , 1955 .

[15]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[16]  Gauthier Gidel,et al.  A Variational Inequality Perspective on Generative Adversarial Networks , 2018, ICLR.

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

[18]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[19]  C. Kanzow,et al.  Relaxation Methods for Generalized Nash Equilibrium Problems with Inexact Line Search , 2009 .

[20]  Mark W. Schmidt,et al.  Ju n 20 18 Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Condition , 2018 .

[21]  Sebastian Bervoets,et al.  Learning with minimal information in continuous games , 2018, Theoretical Economics.

[22]  F. Facchinei,et al.  Finite-Dimensional Variational Inequalities and Complementarity Problems , 2003 .

[23]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[24]  R. Rubinstein,et al.  On relaxation algorithms in computation of noncooperative equilibria , 1994, IEEE Trans. Autom. Control..

[25]  Karthik Sridharan,et al.  Online Learning with Predictable Sequences , 2012, COLT.

[26]  Zhengyuan Zhou,et al.  Learning in games with continuous action sets and unknown payoff functions , 2019, Math. Program..

[27]  Chuan-Sheng Foo,et al.  Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile , 2018, ICLR.

[28]  Z.-Q. Luo,et al.  Error bounds and convergence analysis of feasible descent methods: a general approach , 1993, Ann. Oper. Res..

[29]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[30]  Andrew M. Dai,et al.  Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step , 2017, ICLR.

[31]  Sebastian Nowozin,et al.  Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks , 2017, ICML.

[32]  Alfredo N. Iusem,et al.  Extragradient Method with Variance Reduction for Stochastic Variational Inequalities , 2017, SIAM J. Optim..

[33]  Zheng Xu,et al.  Stabilizing Adversarial Nets With Prediction Methods , 2017, ICLR.

[34]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.