Stochastic optimisation

Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks. Lim, D-Y. & Sabanis, S. 2021. arXiv:2105.13937 [cs.LG]

J. T. Meech and P. Stanley-Marbell, "Efficient Programmable Random Variate Generation Accelerator from Sensor Noise," in IEEE Embedded Systems Letters, doi: 10.1109/LES.2020.3007005

A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating. Sabanis, Sotirios; Zhang, Ying. arXiv:2007.01672 [q-fin.PM]

Taming neural networks with TUSLA : Non-convex learning via adaptive stochastic gradient Langevin algorithms. Lovas, Attila; Lytras, Iosif ; Rásonyi, Miklós ; Sabanis, Sotirios. arXiv:2006.14514 [cs.LG]

Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization. Akyildiz, Ömer Deniz ; Sabanis, Sotirios. arXiv:2002.05465 [math.OC]

Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization. Zhang, Ying ; Akyildiz, Ömer Deniz ; Damoulas, Theo ; Sabanis, Sotirios. 2019. arXiv:1910.02008 [math.ST]

On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case Chau, N. H.; Moulines, É.; Rásonyi, M.; Sabanis, S.; Zhang, Y. 2018. In Print, SIAM Journal on Mathematics of Data Science. arXiv:1905.13142 [math.ST]

Asymptotic Analysis of the LMS Algorithm with Momentum. Gerencsér, L.; Csáji, B. C.; Sabanis, S. 2018 . In: 57th IEEE Annual Conference on Decision and Control, CDC 2018. IEEE, pp. 3062-3067. ISBN 9781538613948

On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case. Barkhagen, M.; Chau, N. H.; Moulines, É. ; Rásonyi, M. ; Sabanis, S.; Zhang, Y. Bernoulli 27(1): 1-33. 2021. DOI: 10.3150/19-BEJ1187