Publications
Journal Article
D.-Y. Lim, A. Neufeld, S. Sabanis, and Y. Zhang: Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function. IMA Journal of Numerical Analysis, 2023.
Y. Zhang, Ö.D. Akyildiz, T. Damoulas, and S. Sabanis: Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization. Applied Mathematics and Optimization, 87(2), 2023.
N. H. Chau, E. Moulines, M. Rásonyi, S. Sabanis, and Y. Zhang: On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case. SIAM Journal on Mathematics of Data Science, 3(3): 959-986, 2021.
M. Barkhagen, N. H. Chau, E. Moulines, M. Rásonyi, S. Sabanis and Y. Zhang: On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case. Bernoulli, 27(1): 1-33, 2021.
S. Sabanis and Y. Zhang: Higher Order Langevin Monte Carlo Algorithm. Electron. J. Statist.: 13(2), 3805-3850, 2019.
S. Sabanis and Y. Zhang: On explicit order 1.5 approximations with varying coefficients: the case of super-linear diffusion coefficients. Journal of Complexity, 50: 84-115, 2019.
Preprints
A. Neufeld and Y. Zhang: Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms. Preprint, 2024. arXiv:2405.05679
A. Neufeld, M. Ng, and Y. Zhang: Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems. Preprint, 2024. arXiv:2403.09532
S. Bruno, Y. Zhang, D.-Y. Lim, Ö.D. Akyildiz, and S. Sabanis: On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates. Preprint, 2023. arXiv:2311.13584
D.-Y. Lim, A. Neufeld, S. Sabanis, and Y. Zhang: Langevin dynamics based algorithm e-THεO POULA for stochastic optimization problems with discontinuous stochastic gradient. Preprint, 2022. arXiv:2210.13193
A. Neufeld, M. Ng, and Y. Zhang: Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting. Preprint, 2022. arXiv:2207.02600
S. Sabanis and Y. Zhang: A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating. Preprint, 2020. arXiv:2007.01672