English
Related papers

Related papers: Approximation and Generalization Abilities of Scor…

200 papers

We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK) are provably sub-optimal and benign overfitting does not…

Machine Learning · Computer Science 2024-06-12 Dan Qiao , Kaiqi Zhang , Esha Singh , Daniel Soudry , Yu-Xiang Wang

Gaussian distributions are commonly used as a key building block in many generative models. However, their applicability has not been well explored in deep networks. In this paper, we propose a novel deep generative model named as Normal…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Jay Nandy , Wynne Hsu , Mong Li Lee

Score-based generative models, which transform noise into data by learning to reverse a diffusion process, have become a cornerstone of modern generative AI. This paper contributes to establishing theoretical guarantees for the probability…

Machine Learning · Statistics 2025-02-03 Jiaqi Tang , Yuling Yan

In recent years, stochastic gradient descent (SGD) based techniques has become the standard tools for training neural networks. However, formal theoretical understanding of why SGD can train neural networks in practice is largely missing.…

Machine Learning · Computer Science 2017-11-03 Yuanzhi Li , Yang Yuan

Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization. However, existing training procedures are limited to images of low resolution (typically below 32x32), and…

Machine Learning · Computer Science 2020-10-27 Yang Song , Stefano Ermon

We establish in this work approximation results of deep neural networks for smooth functions measured in Sobolev norms, motivated by recent development of numerical solvers for partial differential equations using deep neural networks. {Our…

Numerical Analysis · Mathematics 2022-07-25 Sean Hon , Haizhao Yang

Deep generative models (DGM) are neural networks with many hidden layers trained to approximate complicated, high-dimensional probability distributions using a large number of samples. When trained successfully, we can use the DGMs to…

Machine Learning · Computer Science 2021-04-13 Lars Ruthotto , Eldad Haber

Score-based diffusion models are a powerful class of generative models, but their practical use often depends on training neural networks to approximate the score function. Training-free diffusion models provide an attractive alternative by…

Numerical Analysis · Mathematics 2026-01-28 Pengjun Wang , Zezhong Zhang , Minglei Yang , Feng Bao , Yanzhao Cao , Guannan Zhang

Recent advances have significantly improved our understanding of the generalization performance of gradient descent (GD) methods in deep neural networks. A natural and fundamental question is whether GD can achieve generalization rates…

Machine Learning · Computer Science 2026-04-14 Yuanfan Li , Yunwen Lei , Zheng-Chu Guo , Yiming Ying

We discuss the expressive power of neural networks which use the non-smooth ReLU activation function $\varrho(x) = \max\{0,x\}$ by analyzing the approximation theoretic properties of such networks. The existing results mainly fall into two…

Functional Analysis · Mathematics 2019-04-10 Felix Voigtlaender , Philipp Petersen

The classical statistical learning theory implies that fitting too many parameters leads to overfitting and poor performance. That modern deep neural networks generalize well despite a large number of parameters contradicts this finding and…

Machine Learning · Statistics 2022-10-18 Masaaki Imaizumi , Johannes Schmidt-Hieber

We study the asymptotic error of score-based diffusion model sampling in large-sample scenarios from a non-parametric statistics perspective. We show that a kernel-based score estimator achieves an optimal mean square error of…

Statistics Theory · Mathematics 2024-07-25 Kaihong Zhang , Caitlyn H. Yin , Feng Liang , Jingbo Liu

We consider the problem of estimating the parameters of a $d$-dimensional rectified Gaussian distribution from i.i.d. samples. A rectified Gaussian distribution is defined by passing a standard Gaussian distribution through a one-layer ReLU…

Machine Learning · Computer Science 2019-09-20 Shanshan Wu , Alexandros G. Dimakis , Sujay Sanghavi

Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory. It is known that a certain class of multiplicative RNNs…

Machine Learning · Computer Science 2019-01-31 Valentin Khrulkov , Oleksii Hrinchuk , Ivan Oseledets

In Score based Generative Modeling (SGMs), the state-of-the-art in generative modeling, stochastic reverse processes are known to perform better than their deterministic counterparts. This paper delves into the heart of this phenomenon,…

Machine Learning · Computer Science 2023-12-15 Karthik Elamvazhuthi , Samet Oymak , Fabio Pasqualetti

Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution and then learning to reverse this noising process to obtain…

Machine Learning · Statistics 2024-02-20 Joe Benton , Yuyang Shi , Valentin De Bortoli , George Deligiannidis , Arnaud Doucet

We study diffusion and consensus based optimization of a sum of unknown convex objective functions over distributed networks. The only access to these functions is through stochastic gradient oracles, each of which is only available at a…

Numerical Analysis · Computer Science 2015-09-01 N. Denizcan Vanli , Muhammed O. Sayin , Suleyman S. Kozat

Creating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting…

Machine Learning · Computer Science 2021-02-11 Yang Song , Jascha Sohl-Dickstein , Diederik P. Kingma , Abhishek Kumar , Stefano Ermon , Ben Poole

We present Selective Non-Gaussian Refinement (SNGR), a SLAM framework that augments iSAM2 with targeted nested sampling on windows where Gaussian approximations are likely to fail. We detect such regions using the condition number of joint…

Robotics · Computer Science 2026-04-27 Anushka Kulkarni , Sarthak Dubey

We propose a sparse deep ReLU network (SDRN) estimator of the regression function obtained from regularized empirical risk minimization with a Lipschitz loss function. Our framework can be applied to a variety of regression and…

Methodology · Statistics 2024-12-11 Ke Huang , Mingming Liu , Shujie Ma
‹ Prev 1 3 4 5 6 7 10 Next ›