Skip to Main content Skip to Navigation
Conference papers

A Quantitative Analysis Of The Robustness Of Neural Networks For Tabular Data

Kavya Gupta 1, 2 Beatrice Pesquet-Popescu 3 Fateh Kaakai 3 Jean-Christophe Pesquet 1, 2 
2 OPIS - OPtimisation Imagerie et Santé
Inria Saclay - Ile de France, CVN - Centre de vision numérique
Abstract : This paper presents a quantitative approach to demonstrate the robustness of neural networks for tabular data. These data form the backbone of the data structures found in most industrial applications. We analyse the effect of various widely used techniques we encounter in neural network practice, such as regularization of weights, addition of noise to the data, and positivity constraints. This analysis is performed by using three state-of-the-art techniques, which provide mathematical proofs of robustness in terms of Lipschitz constant for feed-forward networks. The experiments are carried out on two prediction tasks and one classification task. Our work brings insights into building robust neural network architectures for safety critical systems that require certification or approval from a competent authority.
Complete list of metadata
Contributor : Kavya Gupta Connect in order to contact the contributor
Submitted on : Thursday, January 20, 2022 - 8:46:52 PM
Last modification on : Friday, February 4, 2022 - 3:20:40 AM
Long-term archiving on: : Thursday, April 21, 2022 - 7:43:09 PM


ICASSP_2021 (3).pdf
Files produced by the author(s)



Kavya Gupta, Beatrice Pesquet-Popescu, Fateh Kaakai, Jean-Christophe Pesquet. A Quantitative Analysis Of The Robustness Of Neural Networks For Tabular Data. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto, Canada. pp.8057-8061, ⟨10.1109/ICASSP39728.2021.9413858⟩. ⟨hal-03527634⟩



Record views


Files downloads