Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning - Archive ouverte HAL
Journal Articles Mathematical Programming Year : 2020

Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning

Abstract

Modern problems in AI or in numerical analysis require nonsmooth approaches with a flexible calculus. We introduce generalized derivatives called conservative fields for which we develop a calculus and provide representation formulas. Functions having a conservative field are called path differentiable: convex, concave, Clarke regular and any semialgebraic Lipschitz continuous functions are path differentiable. Using Whitney stratification techniques for semialgebraic and definable sets, our model provides variational formulas for nonsmooth automatic differentiation oracles, as for instance the famous backpropagation algorithm in deep learning. Our differential model is applied to establish the convergence in values of nonsmooth stochastic gradient methods as they are implemented in practice.

Dates and versions

hal-02521848 , version 1 (27-03-2020)

Identifiers

Cite

Jérôme Bolte, Edouard Pauwels. Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning. Mathematical Programming, 2020, 188 (19-51), ⟨10.1007/s10107-020-01501-5⟩. ⟨hal-02521848⟩
251 View
0 Download

Altmetric

Share

More