We provide theoretical convergence guarantees for score-based generative models (SGMs)
such as denoising diffusion probabilistic models (DDPMs), which constitute the backbone of …

We provide the first polynomial-time convergence guarantees for the probabilistic flow ODE
implementation (together with a corrector step) of score-based generative modeling. Our …

Abstract We study the Unadjusted Langevin Algorithm (ULA) for sampling from a probability
distribution $\nu= e^{-f} $ on $\R^ n $. We prove a convergence guarantee in Kullback …

It is a fundamental problem to understand the complexity of high-accuracy sampling from a
strongly log-concave density π on ℝ d. Indeed, in practice, high-accuracy samplers such as …

Variational inference (VI) seeks to approximate a target distribution $\pi $ by an element of a
tractable family of distributions. Of key interest in statistics and machine learning is Gaussian …

Abstract Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from
unnormalized densities by leveraging the momentum of a particle moving in a potential well …

Statistical Optimal Transport arxiv:2407.18163v2 [math.ST] 7 Nov 2024 Page 1 Statistical
Optimal Transport Sinho Chewi Yale Jonathan Niles-Weed NYU Philippe Rigollet MIT …

We investigate the efficiency of deep neural networks for approximating scoring functions in
diffusion-based generative modeling. While existing approximation theories leverage the …

Bourgain’s slicing problem and KLS isoperimetry up to polylog | Geometric and Functional
Analysis Skip to main content Springer Nature Link Account Menu Find a journal Publish with us …

We propose a sampling algorithm that achieves superior complexity bounds in all the
classical settings (strongly log-concave, log-concave, Logarithmic-Sobolev inequality (LSI) …