中文
相关论文

相关论文: Minimax Estimation of Neural Net Distance

200 篇论文

Evaluating generative adversarial networks (GANs) is inherently challenging. In this paper, we revisit several representative sample-based evaluation metrics for GANs, and address the problem of how to evaluate the evaluation metrics. We…

机器学习 · 计算机科学 2018-08-20 Qiantong Xu , Gao Huang , Yang Yuan , Chuan Guo , Yu Sun , Felix Wu , Kilian Weinberger

Generative adversarial networks (GANs) are unsupervised learning methods for training a generator distribution to produce samples that approximate those drawn from a target distribution. Many such methods can be formulated as minimization…

机器学习 · 统计学 2025-05-13 Jeremiah Birrell

We study the problem of estimating a nonparametric probability density under a large family of losses called Besov IPMs, which include, for example, $\mathcal{L}^p$ distances, total variation distance, and generalizations of both…

统计理论 · 数学 2020-01-14 Ananya Uppal , Shashank Singh , Barnabás Póczos

Although Deep Neural Networks (DNNs) have shown incredible performance in perceptive and control tasks, several trustworthy issues are still open. One of the most discussed topics is the existence of adversarial perturbations, which has…

机器学习 · 计算机科学 2023-01-10 Fabio Brau , Giulio Rossolini , Alessandro Biondi , Giorgio Buttazzo

Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in…

机器学习 · 计算机科学 2018-05-01 Daniel Jiwoong Im , He Ma , Graham Taylor , Kristin Branson

We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical $\mathcal{L}^p$ losses, includes maximum mean discrepancy (MMD), Wasserstein…

We study how well generative adversarial networks (GAN) learn probability distributions from finite samples by analyzing the convergence rates of these models. Our analysis is based on a new oracle inequality that decomposes the estimation…

机器学习 · 计算机科学 2022-05-26 Yunfei Yang

We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However,…

机器学习 · 计算机科学 2017-08-03 Sanjeev Arora , Rong Ge , Yingyu Liang , Tengyu Ma , Yi Zhang

We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs. As our main theoretical contribution, we clarify the situation with bias in GAN loss…

机器学习 · 统计学 2021-01-15 Mikołaj Bińkowski , Danica J. Sutherland , Michael Arbel , Arthur Gretton

In terms of Generative Adversarial Networks (GANs), the information metric to discriminate the generative data from the real data, lies in the key point of generation efficiency, which plays an important role in GAN-based applications,…

机器学习 · 计算机科学 2021-01-08 Rui She , Pingyi Fan

This paper studies the approximation capacity of ReLU neural networks with norm constraint on the weights. We prove upper and lower bounds on the approximation error of these networks for smooth function classes. The lower bound is derived…

机器学习 · 计算机科学 2023-03-31 Yuling Jiao , Yang Wang , Yunfei Yang

We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy…

机器学习 · 计算机科学 2018-03-16 Tim Salimans , Han Zhang , Alec Radford , Dimitris Metaxas

Physics informed neural networks (PINNs) have recently been widely used for robust and accurate approximation of PDEs. We provide rigorous upper bounds on the generalization error of PINNs approximating solutions of the forward problem for…

数值分析 · 数学 2023-12-07 Siddhartha Mishra , Roberto Molinaro

We consider training a deep neural network to generate samples from an unknown distribution given i.i.d. data. We frame learning as an optimization minimizing a two-sample test statistic---informally speaking, a good generator network…

机器学习 · 统计学 2015-05-18 Gintare Karolina Dziugaite , Daniel M. Roy , Zoubin Ghahramani

This paper studies how well generative adversarial networks (GANs) learn probability distributions from finite samples. Our main results establish the convergence rates of GANs under a collection of integral probability metrics defined…

机器学习 · 计算机科学 2022-06-10 Jian Huang , Yuling Jiao , Zhen Li , Shiao Liu , Yang Wang , Yunfei Yang

We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on $n$ independent samples from them. Curiously, we show that estimating the IPM itself between…

统计理论 · 数学 2019-11-05 Tengyuan Liang

Generative adversarial network (GAN) is among the most popular deep learning models for learning complex data distributions. However, training a GAN is known to be a challenging task. This is often attributed to the lack of correlation…

机器学习 · 计算机科学 2020-12-15 Sahil Sidheekh , Aroof Aimen , Vineet Madan , Narayanan C. Krishnan

While likelihood-based inference and its variants provide a statistically efficient and widely applicable approach to parametric inference, their application to models involving intractable likelihoods poses challenges. In this work, we…

统计方法学 · 统计学 2019-06-17 Francois-Xavier Briol , Alessandro Barp , Andrew B. Duncan , Mark Girolami

Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limited due to their…

机器学习 · 计算机科学 2020-10-27 Jeremiah Zhe Liu , Zi Lin , Shreyas Padhy , Dustin Tran , Tania Bedrax-Weiss , Balaji Lakshminarayanan

Classification margins are commonly used to estimate the generalization ability of machine learning models. We present an empirical study of these margins in artificial neural networks. A global estimate of margin size is usually used in…

机器学习 · 计算机科学 2023-02-15 Marthinus W. Theunissen , Coenraad Mouton , Marelie H. Davel
‹ 上一页 1 2 3 10 下一页 ›