10 papers
Trajectory inference via Acceleration Matching
Bartolo Dazzini, Giovanni Conforti, Alain Durmus +1
Trajectory inference is a fundamental problem in many scientific domains: given a collection of unpaired snapshots of observations at discrete time points, the goal is to generate…
Near-Lipschitz stability of the Kim--Milman flow map
Sinho Chewi, Katharina Eichinger, Aram-Alexandre Pooladian
We prove that the Kim--Milman flow map enjoys favorable stability properties with respect to variations in the target measure, provided that one of the target measures is sufficien…
Blind denoising diffusion models and the blessings of dimensionality
Zahra Kadkhodaie, Aram-Alexandre Pooladian, Sinho Chewi +1
Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline rema…
Stability of the Kim--Milman flow map
Sinho Chewi, Aram-Alexandre Pooladian, Matthew S. Zhang
In this short note, we characterize stability of the Kim--Milman flow map -- also known as the probability flow ODE -- with respect to variations in the target measure in relative…
Variational inference via radial transport
Luca Ghafourpour, Sinho Chewi, Alessio Figalli +1
In variational inference (VI), the practitioner approximates a high-dimensional distribution with a simple surrogate one, often a (product) Gaussian distribution. However, in…
Theory and computation for structured variational inference
Shunan Sheng, Bohan Wu, Bennett Zhu +2
Structured variational inference constitutes a core methodology in modern statistical applications. Unlike mean-field variational inference, the approximate posterior is assumed to…