no code implementations • 10 Apr 2023 • László Györfi, Attila Lovas, Miklós Rásonyi
We revisit processes generated by iterated random functions driven by a stationary and ergodic sequence.
no code implementations • 5 Oct 2022 • Attila Lovas, Miklós Rásonyi
We study the mixing properties of an important optimization algorithm of machine learning: the stochastic gradient Langevin dynamics (SGLD) with a fixed step size.
no code implementations • 25 Jun 2020 • Attila Lovas, Iosif Lytras, Miklós Rásonyi, Sotirios Sabanis
We offer a new learning algorithm based on an appropriately constructed variant of the popular stochastic gradient Langevin dynamics (SGLD), which is called tamed unadjusted stochastic Langevin algorithm (TUSLA).
no code implementations • 11 Nov 2019 • Attila Lovas, Miklós Rásonyi
We prove the existence of limiting distributions for a large class of Markov chains on a general state space in a random environment.