5 citations · 5 across the 9 of their papers we have counts for
9 papers
The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
Iosif Lytras, Nikolaos Makras, Sotirios Sabanis
We study the problem of sampling from target distributions whose potentials are simultaneously non-smooth, subject to superlinear gradient growth, and non-convex. We introduce the…
Error estimates for tamed Euler and Randomized Euler schemes for SDEs with locally Lipschitz drift with applications to non-logconcave sampling and optimization
Iosif Lytras, Angelos Ntousis
In this paper, we study the numerical discretization of stochastic differential equations with locally Lipschitz, super-linearly growing drift, and the resulting implications for s…
Contractive kinetic Langevin samplers beyond global Lipschitz continuity
Iosif Lytras, Panayotis Mertikopoulos
In this paper, we examine the problem of sampling from log-concave distributions with (possibly) superlinear gradient growth under kinetic (underdamped) Langevin algorithms. Using…
kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
Iosif Lytras, Sotirios Sabanis, Ying Zhang
Motivated by applications in deep learning, where the global Lipschitz continuity condition is often not satisfied, we examine the problem of sampling from distributions with super…
The Performance Of The Unadjusted Langevin Algorithm Without Smoothness Assumptions
Tim Johnston, Iosif Lytras, Nikolaos Makras +1
In this article, we study the problem of sampling from distributions whose densities are not necessarily smooth nor logconcave. We propose a simple Langevin-based algorithm that do…
Tamed Langevin sampling under weaker conditions
Iosif Lytras, Panayotis Mertikopoulos
Motivated by applications to deep learning which often fail standard Lipschitz smoothness requirements, we examine the problem of sampling from distributions that are not log-conca…
Taming under isoperimetry
Iosif Lytras, Sotirios Sabanis
In this article we propose a novel taming Langevin-based scheme called to sample from distributions with superlinearly growing log-gradient which also satisfy a Lo…
Kinetic Langevin MCMC Sampling Without Gradient Lipschitz Continuity -- the Strongly Convex Case
Tim Johnston, Iosif Lytras, Sotirios Sabanis
In this article we consider sampling from log concave distributions in Hamiltonian setting, without assuming that the objective gradient is globally Lipschitz. We propose two algor…
Taming neural networks with TUSLA: Non-convex learning via adaptive stochastic gradient Langevin algorithms
Attila Lovas, Iosif Lytras, Miklós Rásonyi +1
Artificial neural networks (ANNs) are typically highly nonlinear systems which are finely tuned via the optimization of their associated, non-convex loss functions. In many cases,…