activity
20202026
most citedTaming neural networks with TUSLA: Non-convex learning via adaptive stochastic gradient Langevin algorithms

5 citations · 5 across the 9 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.LG2026

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…

math.PR2026

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…