Bolte, Jérôme and Pauwels, Edouard
(2021)
A mathematical model for automatic differentiation in machine learning.
TSE Working Paper, n. 21-1184, Toulouse

Preview |
Text
Download (444kB) | Preview |
Abstract
Automatic differentiation, as implemented today, does not have a simple mathematical model adapted to the needs of modern machine learning. In this work we articulate the relationships between differentiation of programs as implemented in practice and differentiation of nonsmooth functions. To this end we provide a simple class of functions, a nonsmooth calculus, and show how they apply to stochastic approximation methods. We also evidence the issue of artificial critical points created by algorithmic differentiation and show how usual methods avoid these points with probability one.
Item Type: | Monograph (Working Paper) |
---|---|
Language: | English |
Date: | January 2021 |
Place of Publication: | Toulouse |
Subjects: | B- ECONOMIE ET FINANCE |
Divisions: | TSE-R (Toulouse) |
Institution: | Université Toulouse 1 Capitole |
Site: | UT1 |
Date Deposited: | 04 Mar 2021 16:33 |
Last Modified: | 15 Sep 2021 07:07 |
OAI Identifier: | oai:tse-fr.eu:125195 |
URI: | https://publications.ut-capitole.fr/id/eprint/42369 |
Available Versions of this Item
- A mathematical model for automatic differentiation in machine learning. (deposited 04 Mar 2021 16:33) [Currently Displayed]