Следене
Ying Zhang
Ying Zhang
The Hong Kong University of Science and Technology (Guangzhou)
Потвърден имейл адрес: hkust-gz.edu.cn - Начална страница
Заглавие
Позовавания
Позовавания
Година
On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
NH Chau, É Moulines, M Rásonyi, S Sabanis, Y Zhang
SIAM Journal on Mathematics of Data Science 3 (3), 959-986, 2021
662021
Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization
Y Zhang, ÖD Akyildiz, T Damoulas, S Sabanis
Applied Mathematics & Optimization 87 (2), 25, 2023
472023
On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
M Barkhagen, NH Chau, É Moulines, M Rásonyi, S Sabanis, Y Zhang
Bernoulli 27 (1), 1-33, 2021
432021
Higher order langevin monte carlo algorithm
S Sabanis, Y Zhang
Electronic Journal of Statistics 13 (2), 3805-3850, 2019
232019
On explicit order 1.5 approximations with varying coefficients: the case of super-linear diffusion coefficients
S Sabanis, Y Zhang
Journal of Complexity 50, 84-115, 2019
202019
Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function
DY Lim, A Neufeld, S Sabanis, Y Zhang
IMA Journal of Numerical Analysis, 2023
122023
Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting
A Neufeld, M Ng, Y Zhang
arXiv preprint arXiv:2207.02600, 2022
52022
A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating
S Sabanis, Y Zhang
https://arxiv.org/abs/2007.01672, 0
5*
Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems
A Neufeld, M Ng, Y Zhang
arXiv preprint arXiv:2403.09532, 2024
2024
On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates
S Bruno, Y Zhang, DY Lim, ÖD Akyildiz, S Sabanis
arXiv preprint arXiv:2311.13584, 2023
2023
Langevin dynamics based algorithm e-THO POULA for stochastic optimization problems with discontinuous stochastic gradient
DY Lim, A Neufeld, S Sabanis, Y Zhang
arXiv preprint arXiv:2210.13193, 2022
2022
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–11