Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett
Despite the remarkable empirical success of score-based diffusion models, their statistical guarantees remain underdeveloped. Existing analyses often provide pessimistic convergenc…
stat.ML2026
Optimal Stopping in Latent Diffusion Models
Yu-Han Wu, Quentin Berthet, Gérard Biau +3
We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arg…
stat.ML2025
Building Bridges between Regression, Clustering, and Classification
Lawrence Stewart, Francis Bach, Quentin Berthet
Regression, the task of predicting a continuous scalar target y based on some features x is one of the most fundamental tasks in machine learning and statistics. It has been observ…