collaborators

12 papers

stat.ML2026

Wasserstein Residuals: Learning Gradient Flows from Population Dynamics

Markus Heinonen, Yair Shenfeld, Ricardo Baptista +4

Reconstructing population dynamics is a central problem in the physical and data sciences. Often, the dynamics are modeled as a Wasserstein gradient flow (WGF): a curve of distribu…

math.AP2026

Matrix displacement convexity along density flows

Yair Shenfeld

A new notion of displacement convexity on a matrix level is developed for density flows arising from mean-field games, compressible Euler equations, entropic interpolation, and sem…

math-ph2026

Exact renormalization groups and transportation of measures

Yair Shenfeld

This note provides a new perspective on Polchinski's exact renormalization group, by explaining how it gives rise, via the multiscale Bakry-Émery criterion, to Lipschitz transport…

math.AP2026

Optimal transport maps, majorization, and log-subharmonic measures

Guido De Philippis, Yair Shenfeld

Caffarelli's contraction theorem bounds the derivative of the optimal transport map between a log-convex measure and a strongly log-concave measure. We show that an analogous pheno…

math.PR2026

Intrinsic dimensional functional inequalities on model spaces

Alexandros Eskenazis, Yair Shenfeld

We initiate a systematic study of intrinsic dimensional versions of classical functional inequalities which capture refined properties of the underlying objects. We focus on model…

cs.LG2026

Binomial flows: Denoising and flow matching for discrete ordinal data

Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti

Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, thi…