paper-with-me

Papers

Improved Sample Complexity Bounds for Diffusion Model Training

2023-11-23 · Shivam Gupta, Aditya Parulekar, Eric Price, Zhiyang Xun

Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works~\cite{chen2022,chen2022improved,benton2023linear} have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the \emph{sample complexity} of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work~\cite{BMR20} showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an \emph{exponential improvement} in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.

📄 PDF Abstract BibTeX arXiv:2311.13745

Code (0)

등록된 구현이 없습니다.

Tasks

model

Methods 이 논문이 사용한 방법론

Focus 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

Size-Independent Sample Complexity of Neural Networks

2017-12-18 · Noah Golowich, Alexander Rakhlin, Ohad Shamir

We study the sample complexity of learning neural networks, by providing new bounds on their Rademacher complexity assuming norm constraints on the parameter matrix of each layer. Compared to previous work, these complex…

Sample Complexity of Diffusion Model Training Without Empirical Risk Minimizer Access

2025-05-23 · Mudit Gaur, Prashant Trivedi, Sasidhar Kunapuli, Amrit Singh Bedi 외

Diffusion models have demonstrated state-of-the-art performance across vision, language, and scientific domains. Despite their empirical success, prior theoretical analyses of the sample complexity suffer from poor scali…

Order-Optimal Sample Complexity of Rectified Flows

2026-01-28 · Hari Krishna Sahoo, Mudit Gaur, Vaneet Aggarwal arxiv

Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport trajectories to be linear from the base distrib…

Towards Testing Monotonicity of Distributions Over General Posets

2019-07-06 · Maryam Aliakbarpour, Themis Gouleakis, John Peebles, Ronitt Rubinfeld 외

In this work, we consider the sample complexity required for testing the monotonicity of distributions over partial orders. A distribution $p$ over a poset is monotone if, for any pair of domain elements $x$ and $y$ such…

Sample Complexity Bounds for Influence Maximization

2019-07-31 · Gal Sadeh, Edith Cohen, Haim Kaplan

Influence maximization (IM) is the problem of finding for a given $s\geq 1$ a set $S$ of $|S|=s$ nodes in a network with maximum influence. With stochastic diffusion models, the influence of a set $S$ of seed nodes is de…