DeepAI AI Chat
Log In Sign Up

An SDE Framework for Adversarial Training, with Convergence and Robustness Analysis

by   Haotian Gu, et al.

Adversarial training has gained great popularity as one of the most effective defenses for deep neural networks against adversarial perturbations on data points. Consequently, research interests have grown in understanding the convergence and robustness of adversarial training. This paper considers the min-max game of adversarial training by alternating stochastic gradient descent. It approximates the training process with a continuous-time stochastic-differential-equation (SDE). In particular, the error bound and convergence analysis is established. This SDE framework allows direct comparison between adversarial training and stochastic gradient descent; and confirms analytically the robustness of adversarial training from a (new) gradient-flow viewpoint. This analysis is then corroborated via numerical studies. To demonstrate the versatility of this SDE framework for algorithm design and parameter tuning, a stochastic control problem is formulated for learning rate adjustment, where the advantage of adaptive learning rate over fixed learning rate in terms of training loss is demonstrated through numerical experiments.


page 1

page 2

page 3

page 4


Decreasing scaling transition from adaptive gradient descent to stochastic gradient descent

Currently, researchers have proposed the adaptive gradient descent algor...

A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs

Training neural networks on image datasets generally require extensive e...

Adversarial Training and Provable Robustness: A Tale of Two Objectives

We propose a principled framework that combines adversarial training and...

Domain Adversarial Training: A Game Perspective

The dominant line of work in domain adaptation has focused on learning i...

Generative adversarial training of product of policies for robust and adaptive movement primitives

In learning from demonstrations, many generative models of trajectories ...

Robust Learning via Persistency of Excitation

Improving adversarial robustness of neural networks remains a major chal...

Linear Range in Gradient Descent

This paper defines linear range as the range of parameter perturbations ...