paper-with-me

Papers

Parallel simulation for sampling under isoperimetry and score-based diffusion models

2024-12-10 · Huanjian Zhou, Masashi Sugiyama

In recent years, there has been a surge of interest in proving discretization bounds for sampling under isoperimetry and for diffusion models. As data size grows, reducing the iteration cost becomes an important goal. Inspired by the great success of the parallel simulation of the initial value problem in scientific computation, we propose parallel Picard methods for sampling tasks. Rigorous theoretical analysis reveals that our algorithm achieves better dependence on dimension $d$ than prior works in iteration complexity (i.e., reduced from $\widetilde{O}(\log^2 d)$ to $\widetilde{O}(\log d)$), which is even optimal for sampling under isoperimetry with specific iteration complexity. Our work highlights the potential advantages of simulation methods in scientific computation for dynamics-based sampling and diffusion models.

📄 PDF Abstract BibTeX arXiv:2412.07435

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PICARD 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Fast parallel sampling under isoperimetry

2024-01-17 · Nima Anari, Sinho Chewi, Thuy-Duong Vuong

We show how to sample in parallel from a distribution $\pi$ over $\mathbb R^d$ that satisfies a log-Sobolev inequality and has a smooth log-density, by parallelizing the Langevin (resp. underdamped Langevin) algorithms. …

Point Processes

Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry

2019-11-04 · Andre Wibisono

We study the Proximal Langevin Algorithm (PLA) for sampling from a probability distribution $\nu = e^{-f}$ on $\mathbb{R}^n$ under isoperimetry. We prove a convergence guarantee for PLA in Kullback-Leibler (KL) divergenc…

A Simple Proof of the Mixing of Metropolis-Adjusted Langevin Algorithm under Smoothness and Isoperimetry

2023-04-08 · Yuansi Chen, Khashayar Gatmiry

We study the mixing time of Metropolis-Adjusted Langevin algorithm (MALA) for sampling a target density on $\mathbb{R}^d$. We assume that the target density satisfies $\psi_\mu$-isoperimetry and that the operator norm an…

Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices

2019-03-20 · NeurIPS 2019 12 · Santosh S. Vempala, Andre Wibisono

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

The Geometry of Efficient Nonconvex Sampling

2026-03-26 · Santosh S. Vempala, Andre Wibisono arxiv

We present an efficient algorithm for uniformly sampling from an arbitrary compact body $\mathcal{X} \subset \mathbb{R}^n$ from a warm start under isoperimetry and a natural volume growth condition. Our result provides a…