3 papers
stat.ML2026
Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling
Stanislas Strasman, Gabriel Victorino Cardoso, Sylvain Le Corff +2
Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particl…
stat.ML2026
Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
Stanislas Strasman, Sobihan Surendran, Sylvain Le Corff
Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications. While the statistical properties of their sampling…
math.DG2026
Alexandrov spaces with non negative curvature and displacement convexity of the entropy tensor
Jordan Serres
On a smooth Riemannian manifold, Aishwarya, Rotem and Shenfeld characterised nonnegative sectional curvature as the matrix displacement convexity of an entropy tensor, the Lagrangi…