activity
20202026
most citedRational approximation and its application to improving deep learning classifiers

8 citations · 18 across the 9 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

math.OC2025

KKT-based optimality conditions for neural network approximation

Vinesha Peiris, Nadezda Sukhorukova, Julien Ugon

In this paper, we obtain necessary optimality conditions for neural network approximation. We consider neural networks in Manhattan ( norm) and Chebyshev ( norm). The op…

math.OC2025

Nonsmooth Optimisation and neural networks

Vinesha Peiris, Nadezda Sukhorukova

In this paper, we study neural networks from the point of view of nonsmooth optimisation, namely, quasidifferential calculus. We restrict ourselves to the case of uniform approxima…