Recherche - Archive ouverte HAL Accéder directement au contenu

Filtrer vos résultats

8 résultats
Page :
triés par
Image document

Inertial and Second-order Optimization Algorithms for Training Neural Networks

 Camille Castera
Other [cs.OH]. Institut National Polytechnique de Toulouse - INPT, 2021. English. ⟨NNT : 2021INPT0107⟩
Thèse tel-04186508v1
Image document

An Inertial Newton Algorithm for Deep Learning

 Camille Castera , Jérôme Bolte , Cédric Févotte , Edouard Pauwels
Journal of Machine Learning Research, 2021, 22 (134)
Article dans une revue hal-02140748v6
Image document

Accelerated Gradient Dynamics on Riemannian Manifolds: Faster Rate and Trajectory Convergence

 Tejas Natu , Camille Castera , Jalal Fadili , Peter Ochs
2023
Pré-publication, Document de travail hal-04337117v1
Image document

An Inertial Newton Algorithm for Deep Learning

 Camille Castera , Jérôme Bolte , Cédric Févotte , Edouard Pauwels
Thirty-third Conference on Neural Information Processing Systems : Beyond First Order Methods in ML (NeurIPS Workshop2019), Neural Information Processing Systems Foundation, Dec 2019, Vancouver, Canada
Communication dans un congrès hal-03049921v1
Image document

Inertial Newton Algorithms Avoiding Strict Saddle Points

 Camille Castera
2021
Pré-publication, Document de travail hal-03433202v1
Image document

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

 Severin Maier , Camille Castera , Peter Ochs
2023
Pré-publication, Document de travail hal-04337095v1
Image document

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

 Camille Castera , Cédric Févotte , Jérôme Bolte , Edouard Pauwels
Neural Processing Letters, 2022, pp.1--26. ⟨10.1007/s11063-021-10705-5⟩
Article dans une revue hal-03161775v2
Image document

Continuous Newton-like Methods featuring Inertia and Variable Mass

 Camille Castera , Hedy Attouch , Jalal Fadili , Peter Ochs
2023
Pré-publication, Document de travail hal-03951620v1
Page :