Fast Objective and Duality Gap Convergence for Non-convex Strongly-concave Min-max Problems

06/12/2020
by   Zhishuai Guo, et al.
0

This paper focuses on stochastic methods for solving smooth non-convex strongly-concave min-max problems, which have received increasing attention due to their potential applications in deep learning (e.g., deep AUC maximization). However, most of the existing algorithms are slow in practice, and their analysis revolves around the convergence to a nearly stationary point. We consider leveraging the Polyak-Ł ojasiewicz (PL) condition to design faster stochastic algorithms with stronger convergence guarantee. Although PL condition has been utilized for designing many stochastic minimization algorithms, their applications for non-convex min-max optimization remains rare. In this paper, we propose and analyze proximal epoch-based methods, and establish fast convergence in terms of both the primal objective gap and the duality gap. Our analysis is interesting in threefold: (i) it is based on a novel Lyapunov function that consists of the primal objective gap and the duality gap of a regularized function; (ii) it only requires a weaker PL condition for establishing the primal objective convergence than that required for the duality gap convergence; (iii) it yields the optimal dependence on the accuracy level ϵ, i.e., O(1/ϵ). We also make explicit the dependence on the problem parameters and explore regions of weak convexity parameter that lead to improved dependence on condition numbers. Experiments on deep AUC maximization demonstrate the effectiveness of our methods. Our method also beats the 1st place on Stanford CheXpert competition in terms of AUC on the public validation set.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/13/2020

Sharp Analysis of Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization

Epoch gradient descent method (a.k.a. Epoch-GD) proposed by (Hazan and K...
10/04/2018

Non-Convex Min-Max Optimization: Provable Algorithms and Applications in Machine Learning

Min-max saddle-point problems have broad applications in many tasks in m...
06/01/2022

Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximization

In this paper, we study multi-block min-max bilevel optimization problem...
03/01/2017

Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization

Iterative Hard Thresholding (IHT) is a class of projected gradient desce...
05/05/2020

Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks

In this paper, we study distributed algorithms for large-scale AUC maxim...
02/09/2021

Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity

eep UC (area under the ROC curve) aximization (DAM) has attracted much a...
03/01/2022

When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee

In this paper, we propose systematic and efficient gradient-based method...

Please sign up or login with your details

Forgot password? Click here to reset