Log In Sign Up

Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML

by   Sijia Liu, et al.

In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled optimization framework, integrating a zeroth-order (ZO) gradient estimator with an alternating projected stochastic gradient descent-ascent method, where the former only requires a small number of function queries and the later needs just one-step descent/ascent update. We show that the proposed framework, referred to as ZO-Min-Max, has a sub-linear convergence rate under mild conditions and scales gracefully with problem size. From an application side, we explore a promising connection between black-box min-max optimization and black-box evasion and poisoning attacks in adversarial machine learning (ML). Our empirical evaluations on these use cases demonstrate the effectiveness of our approach and its scalability to dimensions that prohibit using recent black-box solvers.


page 1

page 2

page 3

page 4


Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework

In this work, we focus on the study of stochastic zeroth-order (ZO) opti...

Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent

Despite the great achievements of the modern deep neural networks (DNNs)...

Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity

ℓ_0 constrained optimization is prevalent in machine learning, particula...

Distributionally Constrained Black-Box Stochastic Gradient Estimation and Optimization

We consider stochastic gradient estimation using only black-box function...

Learning to Learn by Zeroth-Order Oracle

In the learning to learn (L2L) framework, we cast the design of optimiza...

Black-box α-divergence Minimization

Black-box alpha (BB-α) is a new approximate inference method based on th...

Solving Constrained CASH Problems with ADMM

The CASH problem has been widely studied in the context of automated con...