Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization

1 code implementation • 16 Nov 2023 • Severin Maier, Camille Castera, Peter Ochs

We introduce an autonomous system with closed-loop damping for first-order convex optimization.

Inertial Newton Algorithms Avoiding Strict Saddle Points

1 code implementation • 8 Nov 2021 • Camille Castera

We study the asymptotic behavior of second-order algorithms mixing Newton's method and inertial gradient descent in non-convex landscapes.

Second-order step-size tuning of SGD for non-convex optimization

1 code implementation • 5 Mar 2021 • Camille Castera, Jérôme Bolte, Cédric Févotte, Edouard Pauwels

In view of a direct and simple improvement of vanilla SGD, this paper presents a fine-tuning of its step-sizes in the mini-batch case.

An Inertial Newton Algorithm for Deep Learning

2 code implementations • 29 May 2019 • Camille Castera, Jérôme Bolte, Cédric Févotte, Edouard Pauwels

We prove the convergence of INNA for most deep learning problems.

General Classification Image Classification