72 citations · 188 across the 26 of their papers we have counts for
7 papers · 1 filter
Simulation-Free Learning of Population Dynamics with Wasserstein Lagrangian Residuals
Fedor Sergeev, Markus Heinonen, Daniel Waxman +4
The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this evolution from unpaired snapsh…
Jumping up and down: Denoiser diffusion models for discrete ordinal data
Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti
Diffusion models are highly developed in continuous spaces for image and video domains. Recently, major advances have been made for discrete diffusion models for categorical data,…
One-Step Generative Surrogate Models via Block-Triangular Joint Drifting
Nicholas Geissler, Shreya Jha, Ricardo Baptista +1
Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of the next state conditioned o…
Approximating Measures on Function Spaces: Transport and Truncation
Ricardo Baptista, Bamdad Hosseini, Alexander W. Hsu
Measures on function spaces arise throughout Bayesian inverse problems and generative modeling, often with low-dimensional structure relative to a tractable reference measure. We i…
Gradient-free Riemannian Langevin Sampler
Ricardo Baptista, Olivier Zahm
We address the problem of efficiently sampling multimodal probability distributions, where standard Markov Chain Monte Carlo methods often suffer from poor mixing and mode trapping…
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…
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…