← Search

Cedric Gouy-Pailler

2 accepted papers

2019

Theoretical evidence for adversarial robustness through randomization

NeurIPS 2019poster

This paper investigates the theory of robustness against adversarial attacks. It focuses on the family of randomization techniques that consist in injecting noise in the network at inference time. These techniques have proven effective in many contexts, but lack theoretical arguments. We close this…

Cited by 113SourcePDFScholar
2017

Structured adaptive and random spinners for fast machine learning computations

AISTATS 2017poster

We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy. The proposed framework relies on projections via structured matrices that we call Structured Spinners, which are formed as products of three structured matrix-blocks…

Cited by 42SourcePDFScholar