4 papers
From Global to Tail Convergence: Dynamics of -Stable Score-Based Generative Models
Ianis Hammani, Claire Boyer
Score-based generative models driven by -stable L{é}vy processes have been proposed as an alternative to Brownian diffusion models, with empirical evidence suggesting improved s…
Attention-based PCA
Rodrigo Maulen-Soto, Claire Boyer
We study attention mechanisms through the lens of a canonical unsupervised problem: principal component analysis (PCA). We show that, when trained on Gaussian data, both softmax an…
Wasserstein Convergence of Critically Damped Langevin Diffusions
Stanislas Strasman, Sobihan Surendran, Claire Boyer +3
Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications and benefit from strong theoretical guarantees. Rec…
An analysis of the noise schedule for score-based generative models
Stanislas Strasman, Antonio Ocello, Claire Boyer +2
Score-based generative models (SGMs) aim at estimating a target data distribution by learning score functions using only noise-perturbed samples from the target.Recent literature h…