Elen Vardanyan — accepted AI-conference papers

2025

Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds

Vahan Arsenyan, Elen Vardanyan, Arnak S. Dalalyan

NeurIPS 2025poster

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, denoising diffusion probabilistic models (DDPMs) construct such examples by mapping a Brownian motion via a diffusion process dr…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution

Elen Vardanyan, Sona Hunanyan, Tigran Galstyan, Arshak Minasyan, Arnak S. Dalalyan

ICML 2024poster

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 focused on quantifying the statistical precision of popular algorithms, there is a lack of mathematical evaluation regarding…

Cited by 1 Source ↗PDF ↗Scholar ↗