Iosif Lytras

According to our database, Iosif Lytras authored at least 9 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

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

CoRR, May, 2026

2025

Contractive kinetic Langevin samplers beyond global Lipschitz continuity.

Iosif Lytras, Panagiotis Mertikopoulos

CoRR, September, 2025

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients.

Iosif Lytras, Sotirios Sabanis, Ying Zhang

CoRR, June, 2025

The Performance Of The Unadjusted Langevin Algorithm Without Smoothness Assumptions.

Tim Johnston, Iosif Lytras, Nikolaos Makras, Sotirios Sabanis

Trans. Mach. Learn. Res., 2025

Tamed Langevin sampling under weaker conditions.

Iosif Lytras, Panayotis Mertikopoulos

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Kinetic Langevin MCMC sampling without gradient Lipschitz continuity - the strongly convex case.

Tim Johnston, Iosif Lytras, Sotirios Sabanis

J. Complex., 2024

2023

Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms.

Attila Lovas, Iosif Lytras, Miklós Rásonyi, Sotirios Sabanis

SIAM J. Math. Data Sci., June, 2023

Taming under isoperimetry.

Iosif Lytras, Sotirios Sabanis

CoRR, 2023

2020

Taming neural networks with TUSLA: Non-convex learning via adaptive stochastic gradient Langevin algorithms.

Attila Lovas, Iosif Lytras, Miklós Rásonyi, Sotirios Sabanis

CoRR, 2020