Articles with public access mandates - Sotirios SabanisLearn more
Available somewhere: 15
The tamed unadjusted Langevin algorithm
N Brosse, A Durmus, É Moulines, S Sabanis
Stochastic Processes and their Applications 129 (10), 3638-3663, 2019
Mandates: UK Engineering and Physical Sciences Research Council
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
Mandates: Hungarian Academy of Sciences, UK Engineering and Physical Sciences Research …
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
Mandates: Hungarian Academy of Sciences, UK Engineering and Physical Sciences Research …
Taming neural networks with tusla: Nonconvex learning via adaptive stochastic gradient langevin algorithms
A Lovas, I Lytras, M Rásonyi, S Sabanis
SIAM Journal on Mathematics of Data Science 5 (2), 323-345, 2023
Mandates: Hungarian Academy of Sciences, UK Engineering and Physical Sciences Research …
Higher order langevin monte carlo algorithm
S Sabanis, Y Zhang
Mandates: UK Engineering and Physical Sciences Research Council
Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization
ÖD Akyildiz, S Sabanis
arXiv preprint arXiv:2002.05465, 2020
Mandates: UK Engineering and Physical Sciences Research Council
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
Mandates: UK Engineering and Physical Sciences Research Council
On fixed gain recursive estimators with discontinuity in the parameters
HN Chau, C Kumar, M Rásonyi, S Sabanis
ESAIM: Probability and Statistics 23, 217-244, 2019
Mandates: Hungarian Academy of Sciences, UK Engineering and Physical Sciences Research …
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 44 (3), 1464-1559, 2024
Mandates: UK Engineering and Physical Sciences Research Council, European Commission
Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
DY Lim, S Sabanis
Journal of Machine Learning Research 25 (53), 1-52, 2024
Mandates: European Commission
Statistical finite elements via Langevin dynamics
ÖD Akyildiz, C Duffin, S Sabanis, M Girolami
SIAM/ASA Journal on Uncertainty Quantification 10 (4), 1560-1585, 2022
Mandates: UK Engineering and Physical Sciences Research Council
Optimising portfolio diversification and dimensionality
M Barkhagen, S García, J Gondzio, J Kalcsics, J Kroeske, S Sabanis, ...
Journal of Global Optimization 85 (1), 185-234, 2023
Mandates: UK Engineering and Physical Sciences Research Council
Langevin Dynamics Based Algorithm e-THεO POULA for Stochastic Optimization Problems with Discontinuous Stochastic Gradient
DY Lim, A Neufeld, S Sabanis, Y Zhang
Mathematics of Operations Research, 2024
Mandates: UK Engineering and Physical Sciences Research Council, European Commission
Portfolio diversification based on ratios of risk measures
M Barkhagen, B Fleming, SG Quiles, J Gondzio, J Kalcsics, J Kroeske, ...
Mandates: UK Engineering and Physical Sciences Research Council
Asymptotic Analysis of the LMS Algorithm with Momentum
L Gerencsér, BC Csáji, S Sabanis
2018 IEEE Conference on Decision and Control (CDC), 3062-3067, 2018
Mandates: Hungarian Academy of Sciences, UK Engineering and Physical Sciences Research …
Publication and funding information is determined automatically by a computer program