Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm

In this work, we study the computational complexity of reducing the squared gradient magnitude for smooth minimax optimization problems. First, we present algorithms with accelerated O(1/k) last-iterate rates, faster than the existing O(1/k) or slower rates for extragradient, Popov, and gradient descent with anchoring. The acceleration mechanism combines extragradient steps with anchoring and is distinct from Nesterov’s acceleration. We then establish optimality of the O(1/k) rate through a matching lower bound.

[1]  Arkadi S. Nemirovsky,et al.  Information-based complexity of linear operator equations , 1992, J. Complex..

[2]  Bang Công Vu,et al.  A splitting algorithm for dual monotone inclusions involving cocoercive operators , 2011, Advances in Computational Mathematics.

[3]  John Darzentas,et al.  Problem Complexity and Method Efficiency in Optimization , 1983 .

[4]  Yurii Nesterov,et al.  Smooth minimization of non-smooth functions , 2005, Math. Program..

[5]  Yurii Nesterov,et al.  Primal-dual subgradient methods for convex problems , 2005, Math. Program..

[6]  Yi Zhou,et al.  Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry , 2021, ICLR.

[7]  Noah Golowich,et al.  Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems , 2020, COLT.

[8]  Francis Bach,et al.  Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions , 2019, COLT.

[9]  Prateek Jain,et al.  Efficient Algorithms for Smooth Minimax Optimization , 2019, NeurIPS.

[10]  A. Juditsky,et al.  Solving variational inequalities with Stochastic Mirror-Prox algorithm , 2008, 0809.0815.

[11]  Michael I. Jordan,et al.  Minmax Optimization: Stable Limit Points of Gradient Descent Ascent are Locally Optimal , 2019, ArXiv.

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

[13]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[14]  Rong Jin,et al.  25th Annual Conference on Learning Theory Online Optimization with Gradual Variations , 2022 .

[15]  Guanghui Lan,et al.  An optimal method for stochastic composite optimization , 2011, Mathematical Programming.

[16]  Yura Malitsky,et al.  Golden ratio algorithms for variational inequalities , 2018, Mathematical Programming.

[17]  Paul Tseng,et al.  A Modified Forward-backward Splitting Method for Maximal Monotone Mappings 1 , 1998 .

[18]  Ioannis Mitliagkas,et al.  Negative Momentum for Improved Game Dynamics , 2018, AISTATS.

[19]  Laurent Condat,et al.  A Primal–Dual Splitting Method for Convex Optimization Involving Lipschitzian, Proximable and Linear Composite Terms , 2012, Journal of Optimization Theory and Applications.

[20]  Renbo Zhao,et al.  Optimal Stochastic Algorithms for Convex-Concave Saddle-Point Problems , 2019 .

[21]  Guodong Zhang,et al.  A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints , 2020, J. Mach. Learn. Res..

[22]  B. Halpern.  Fixed points of nonexpanding maps , 1967 .

[23]  Panayotis Mertikopoulos,et al.  On the convergence of single-call stochastic extra-gradient methods , 2019, NeurIPS.

[24]  Michael I. Jordan,et al.  Near-Optimal Algorithms for Minimax Optimization , 2020, COLT.

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

[26]  Yoel Drori,et al.  The exact information-based complexity of smooth convex minimization , 2016, J. Complex..

[27]  Antonin Chambolle,et al.  A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging , 2011, Journal of Mathematical Imaging and Vision.

[28]  P. Tseng.  On linear convergence of iterative methods for the variational inequality problem , 1995 .

[29]  Antonin Chambolle,et al.  On the ergodic convergence rates of a first-order primal–dual algorithm , 2016, Math. Program..

[30]  Niao He,et al.  A Catalyst Framework for Minimax Optimization , 2020, NeurIPS.

[31]  Yair Censor,et al.  The Subgradient Extragradient Method for Solving Variational Inequalities in Hilbert Space , 2011, J. Optim. Theory Appl..

[32]  M. Solodov,et al.  A Hybrid Approximate Extragradient – Proximal Point Algorithm Using the Enlargement of a Maximal Monotone Operator , 1999 .

[33]  Renato D. C. Monteiro,et al.  An Accelerated HPE-Type Algorithm for a Class of Composite Convex-Concave Saddle-Point Problems , 2016, SIAM J. Optim..

[34]  S. I. Lyashko,et al.  Low-cost modification of Korpelevich’s methods for monotone equilibrium problems , 2011 .

[35]  Yu. V. Malitsky,et al.  An Extragradient Algorithm for Monotone Variational Inequalities , 2014 .

[36]  Tengyuan Liang,et al.  Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks , 2018, AISTATS.

[37]  Meisam Razaviyayn,et al.  Efficient Search of First-Order Nash Equilibria in Nonconvex-Concave Smooth Min-Max Problems , 2021, SIAM J. Optim..

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

[39]  Yunmei Chen,et al.  Accelerated schemes for a class of variational inequalities , 2014, Mathematical Programming.

[40]  N. S. Aybat,et al.  A Primal-Dual Algorithm for General Convex-Concave Saddle Point Problems , 2018, 1803.01401.

[41]  Saeed Ghadimi,et al.  Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms , 2013, SIAM J. Optim..

[42]  Saeed Ghadimi,et al.  Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework , 2012, SIAM J. Optim..

[43]  Kun Yuan,et al.  ODE Analysis of Stochastic Gradient Methods with Optimism and Anchoring for Minimax Problems and GANs , 2019, ArXiv.

[44]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[45]  Ohad Shamir,et al.  On Lower and Upper Bounds in Smooth and Strongly Convex Optimization , 2016, J. Mach. Learn. Res..

[46]  Ioannis Mitliagkas,et al.  A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games , 2020, AISTATS.

[47]  M. Noor.  New extragradient-type methods for general variational inequalities , 2003 .

[48]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

[49]  Adrien B. Taylor,et al.  Smooth strongly convex interpolation and exact worst-case performance of first-order methods , 2015, Mathematical Programming.

[50]  Renato D. C. Monteiro,et al.  On the Complexity of the Hybrid Proximal Extragradient Method for the Iterates and the Ergodic Mean , 2010, SIAM J. Optim..

[51]  Aryan Mokhtari,et al.  A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach , 2019, AISTATS.

[52]  Matthew K. Tam,et al.  A Forward-Backward Splitting Method for Monotone Inclusions Without Cocoercivity , 2018, SIAM J. Optim..

[53]  Shuzhong Zhang,et al.  On lower iteration complexity bounds for the convex concave saddle point problems , 2019, Math. Program..

[54]  Nathan Srebro,et al.  Tight Complexity Bounds for Optimizing Composite Objectives , 2016, NIPS.

[55]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[56]  Yuanhao Wang,et al.  Improved Algorithms for Convex-Concave Minimax Optimization , 2020, NeurIPS.

[57]  Jelena Diakonikolas.  Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions to Variational Inequalities , 2020, COLT.

[58]  Ming Yan,et al.  A new primal-dual algorithm for minimizing the sum of three functions with a linear operator , 2016, 1611.09805.

[59]  Michael I. Jordan,et al.  On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems , 2019, ICML.

[60]  RockaJellm.  MONOTONE OPERATORS ASSOCIATED WITH SADDLE . FUNCTIONS AND MINIMAX PROBLEMS R . 1 ' , 2022 .

[61]  A. Gasnikov,et al.  Accelerated Methods for Saddle-Point Problem , 2020, Computational Mathematics and Mathematical Physics.

[62]  Yurii Nesterov,et al.  Excessive Gap Technique in Nonsmooth Convex Minimization , 2005, SIAM J. Optim..

[63]  Arkadi S. Nemirovsky,et al.  On optimality of Krylov's information when solving linear operator equations , 1991, J. Complex..

[64]  Felix Lieder,et al.  On the convergence rate of the Halpern-iteration , 2020, Optim. Lett..

[65]  Yangyang Xu,et al.  Lower complexity bounds of first-order methods for convex-concave bilinear saddle-point problems , 2018, Math. Program..

[66]  Arkadi Nemirovski,et al.  Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems , 2004, SIAM J. Optim..

[67]  Marc Teboulle,et al.  Performance of first-order methods for smooth convex minimization: a novel approach , 2012, Mathematical Programming.

[68]  L. Popov.  A modification of the Arrow-Hurwicz method for search of saddle points , 1980 .

[69]  Ohad Shamir,et al.  On the Iteration Complexity of Oblivious First-Order Optimization Algorithms , 2016, ICML.

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

[71]  Yurii Nesterov,et al.  Dual extrapolation and its applications to solving variational inequalities and related problems , 2003, Math. Program..

[72]  Matthew K. Tam,et al.  Shadow Douglas–Rachford Splitting for Monotone Inclusions , 2019, Applied Mathematics & Optimization.

[73]  Karthik Sridharan,et al.  Optimization, Learning, and Games with Predictable Sequences , 2013, NIPS.

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

[75]  Yu. V. Malitsky,et al.  Projected Reflected Gradient Methods for Monotone Variational Inequalities , 2015, SIAM J. Optim..

[76]  Renato D. C. Monteiro,et al.  Complexity of Variants of Tseng's Modified F-B Splitting and Korpelevich's Methods for Hemivariational Inequalities with Applications to Saddle-point and Convex Optimization Problems , 2011, SIAM J. Optim..

[77]  Patrick L. Combettes,et al.  A Warped Resolvent Algorithm to Construct Nash Equilibria , 2021 .

[78]  Yongxin Chen,et al.  Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications , 2019, IEEE Transactions on Signal Processing.

[79]  Yurii Nesterov,et al.  Solving Strongly Monotone Variational and Quasi-Variational Inequalities , 2006 .

[80]  Jason D. Lee,et al.  Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods , 2019, NeurIPS.

[81]  Constantinos Daskalakis,et al.  Near-optimal no-regret algorithms for zero-sum games , 2011, SODA '11.

[82]  Haipeng Luo,et al.  Fast Convergence of Regularized Learning in Games , 2015, NIPS.

[83]  Yunmei Chen,et al.  Optimal Primal-Dual Methods for a Class of Saddle Point Problems , 2013, SIAM J. Optim..

[84]  Wei Peng,et al.  Training GANs with centripetal acceleration , 2019, Optim. Methods Softw..

[85]  Kimon Antonakopoulos,et al.  Adaptive extra-gradient methods for min-max optimization and games , 2020, ICLR.