Suivre
Camille Castera
Camille Castera
University of Bordeaux
Adresse e-mail validée de math.u-bordeaux.fr - Page d'accueil
Titre
Citée par
Citée par
Année
An inertial newton algorithm for deep learning
C Castera, J Bolte, C Févotte, E Pauwels
Journal of Machine Learning Research 22 (134), 1-31, 2021
78*2021
Second-order step-size tuning of SGD for non-convex optimization
C Castera, J Bolte, C Févotte, E Pauwels
Neural Processing Letters 54 (3), 1727-1752, 2022
132022
Continuous Newton-like methods featuring inertia and variable mass
C Castera, H Attouch, J Fadili, P Ochs
SIAM Journal on Optimization 34 (1), 251-277, 2024
52024
Inertial Newton algorithms avoiding strict saddle points
C Castera
Journal of Optimization Theory and Applications 199 (3), 881-903, 2023
42023
From Learning to Optimize to Learning Optimization Algorithms
C Castera, P Ochs
arXiv preprint arXiv:2405.18222, 2024
22024
Accelerated Gradient Dynamics on Riemannian Manifolds: Faster Rate and Trajectory Convergence
T Natu, C Castera, J Fadili, P Ochs
arXiv preprint arXiv:2312.06366, 2023
2023
Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization
S Maier, C Castera, P Ochs
arXiv preprint arXiv:2311.10053, 2023
2023
Inertial and Second-order Optimization Algorithms for Training Neural Networks
C Castera
Institut National Polytechnique de Toulouse-INPT, 2021
2021
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–8