Showing math.PRShow all
3 papers · 1 filter
math.PR2026
On ergodicity of the SAGA-LD algorithm
Miklós Rásonyi
The so-called SAGA-LD algorithm is used for efficient sampling from high-dimensional distributions in machine learning. Its intricate dynamics resists standard approaches of Markov…
math.PR2025
Sharp Mixing Rates for Markov Chains on General Spaces with Unbounded Random Environments
Attila Lovas, Miklós Rásonyi, Lionel Truquet
We consider Markov chains on general state spaces in stationary random environment which are defined by a random mapping that is contractive up to a bounded perturbation. We prove…
math.PR2025
Rate estimates for weighted total variation norm in terms of Wasserstein distances
Iván Ivkovic, Miklós Rásonyi
We study the weighted total variation distance between probability measures. Using Fourier-analytic tools, we present estimates in terms of Wasserstein distances between the respec…