Skip to Main content Skip to Navigation
Conference papers

A mathematical model for automatic differentiation in machine learning

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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02734446
Contributor : Edouard Pauwels <>
Submitted on : Tuesday, June 2, 2020 - 1:59:14 PM
Last modification on : Friday, October 30, 2020 - 3:28:54 AM

Files

backport2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02734446, version 1
  • ARXIV : 2006.02080

Citation

Jerome Bolte, Edouard Pauwels. A mathematical model for automatic differentiation in machine learning. Conference on Neural Information Processing Systems, Dec 2020, Vancouver, Canada. ⟨hal-02734446v1⟩

Share

Metrics

Record views

82

Files downloads

75