Adrien Taylor
Adrien Taylor
Inria - ENS Paris
Bekræftet mail på - Startside
Citeret af
Citeret af
Smooth strongly convex interpolation and exact worst-case performance of first-order methods
AB Taylor, JM Hendrickx, F Glineur
Mathematical Programming 161 (1-2), 307-345, 2017
Exact worst-case performance of first-order methods for composite convex optimization
AB Taylor, JM Hendrickx, F Glineur
SIAM Journal on Optimization 27 (3), 1283-1313, 2017
On the worst-case complexity of the gradient method with exact line search for smooth strongly convex functions
E De Klerk, F Glineur, AB Taylor
Optimization Letters 11 (7), 1185-1199, 2017
Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions
A Taylor, F Bach
Proceedings of the Thirty-Second Conference on Learning Theory (COLT), 2019
Exact worst-case convergence rates of the proximal gradient method for composite convex minimization
AB Taylor, JM Hendrickx, F Glineur
Journal of Optimization Theory and Applications 178 (2), 455-476, 2018
Operator splitting performance estimation: Tight contraction factors and optimal parameter selection
EK Ryu, AB Taylor, C Bergeling, P Giselsson
SIAM Journal on Optimization 30 (3), 2251-2271, 2020
Convex interpolation and performance estimation of first-order methods for convex optimization.
AB Taylor
Catholic University of Louvain, Louvain-la-Neuve, Belgium, 2017
Optimal complexity and certification of Bregman first-order methods
RA Dragomir, AB Taylor, A d’Aspremont, J Bolte
Mathematical Programming, 1-43, 2021
Lyapunov functions for first-order methods: Tight automated convergence guarantees
A Taylor, B Van Scoy, L Lessard
International Conference on Machine Learning (ICML) 80, 4897--4906, 2018
Efficient first-order methods for convex minimization: a constructive approach
Y Drori, AB Taylor
Mathematical Programming 184 (1), 183-220, 2020
Performance estimation toolbox (PESTO): automated worst-case analysis of first-order optimization methods
AB Taylor, JM Hendrickx, F Glineur
2017 IEEE 56th Annual Conference on Decision and Control (CDC), 1278-1283, 2017
Worst-case convergence analysis of inexact gradient and Newton methods through semidefinite programming performance estimation
E De Klerk, F Glineur, AB Taylor
SIAM Journal on Optimization 30 (3), 2053-2082, 2020
Acceleration methods
A d'Aspremont, D Scieur, A Taylor
arXiv preprint arXiv:2101.09545, 2021
An optimal gradient method for smooth strongly convex minimization
A Taylor, Y Drori
arXiv preprint arXiv:2101.09741, 2021
Principled analyses and design of first-order methods with inexact proximal operators
M Barré, A Taylor, F Bach
arXiv preprint arXiv:2006.06041, 2020
On the oracle complexity of smooth strongly convex minimization
Y Drori, A Taylor
Journal of Complexity, 2021
Complexity Guarantees for Polyak Steps with Momentum
M Barré, A Taylor, A d'Aspremont
Proceedings of the Thirty-Third Conference on Learning Theory (COLT), 2020
Convergence of constrained anderson acceleration
M Barré, A Taylor, A d'Aspremont
arXiv preprint arXiv:2010.15482, 2020
A note on approximate accelerated forward-backward methods with absolute and relative errors, and possibly strongly convex objectives
M Barré, A Taylor, F Bach
arXiv preprint arXiv:2106.15536, 2021
Super-Acceleration with Cyclical Step-sizes
B Goujaud, D Scieur, A Dieuleveut, A Taylor, F Pedregosa
arXiv preprint arXiv:2106.09687, 2021
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–20