Can overfitted deep neural networks in adversarial training generalize? – An approximation viewpoint streaming

'Info?'

Production companies

University of Warwick

tagline

Analysis

Genre

Documentary, Crime

runtime	Genre	revenue
52 min	Documentary	0 USD
	Crime

.

Download link for "Can overfitted deep neural networks in adversarial training generalize? – An approximation viewpoint" :

DOWNLOAD (700MG)

SYNOPIS

In this talk, I will discuss whether overfitted DNNs in adversarial training can generalize from an approximation viewpoint. We prove by construction the existence of infinitely many adversarial training classifiers on over-parameterized DNNs that obtain arbitrarily small adversarial training error (overfitting), whereas achieving good robust generalization error under certain conditions concerning the data quality, well separated, and perturbation level. This construction is optimal and thus points out the fundamental limits of DNNs under adversarial training with statistical guarantees. Part of this talk comes from our recent work.