192 citations · 1.1k across the 46 of their papers we have counts for
51 papers
Universal Local Error and Realized Amplification for the First-Order EDM Predictor
Nicolas Brosse, Arnak S. Dalalyan
We analyze the first-order deterministic diffusion sampler of Karras et al. (2022), termed EDM, in 2-Wasserstein distance by separating two sources of error: local discretization e…
Boundary-layer asymptotics for Gaussian-smoothed singular measures
Nicolas Brosse, Arnak S. Dalalyan
We study the small-noise asymptotics of Euclidean heat regularizations of probability measures supported on manifolds with corners. Near a boundary or corner stratum, the relevant…
Improved Guarantees for Langevin Monte Carlo with Average Smoothness
Arnak S. Dalalyan, Avetik Karagulyan
We establish improved nonasymptotic bounds for Langevin Monte Carlo in the strongly log-concave setting, when the error is measured by the Wasserstein distance. The main result sho…
Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal Bounds
Vahan Arsenyan, Elen Vardanyan, Arnak Dalalyan
Generative modeling aims to produce new random examples from an unknown target distribution, given access to a finite collection of examples. Among the leading approaches, denoisin…
Parallelized Midpoint Randomization for Langevin Monte Carlo
Lu Yu, Arnak Dalalyan
We study the problem of sampling from a target probability density function in frameworks where parallel evaluations of the log-density gradient are feasible. Focusing on smooth an…
Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
Elen Vardanyan, Sona Hunanyan, Tigran Galstyan +2
This paper explores the problem of generative modeling, aiming to simulate diverse examples from an unknown distribution based on observed examples. While recent studies have focus…