中文
相关论文

相关论文: Rates of convergence for nonparametric estimation …

200 篇论文

We provide non asymptotic rates of convergence of the Wasserstein Generative Adversarial networks (WGAN) estimator. We build neural networks classes representing the generators and discriminators which yield a GAN that achieves the minimax…

统计理论 · 数学 2025-03-13 Arthur Stéphanovitch , Eddie Aamari , Clément Levrard

The mathematical forces at work behind Generative Adversarial Networks raise challenging theoretical issues. Motivated by the important question of characterizing the geometrical properties of the generated distributions, we provide a…

Generative Adversarial Networks (GANs) have achieved great success in data generation. However, its statistical properties are not fully understood. In this paper, we consider the statistical behavior of the general $f$-divergence…

统计理论 · 数学 2022-09-16 Xinwei Shen , Kani Chen , Tong Zhang

Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limited in two ways. They often learn distributions with low…

机器学习 · 统计学 2019-10-11 Adji B. Dieng , Francisco J. R. Ruiz , David M. Blei , Michalis K. Titsias

One of the most significant challenges in statistical signal processing and machine learning is how to obtain a generative model that can produce samples of large-scale data distribution, such as images and speeches. Generative Adversarial…

计算机视觉与模式识别 · 计算机科学 2020-05-28 Pegah Salehi , Abdolah Chalechale , Maryam Taghizadeh

Generative Adversarial Networks (GANs) have become a widely popular framework for generative modelling of high-dimensional datasets. However their training is well-known to be difficult. This work presents a rigorous statistical analysis of…

机器学习 · 统计学 2017-10-17 Mathieu Sinn , Ambrish Rawat

Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to…

机器学习 · 统计学 2015-05-22 Ian J. Goodfellow

Generative Adversarial Network (GAN) and its variants exhibit state-of-the-art performance in the class of generative models. To capture higher-dimensional distributions, the common learning procedure requires high computational complexity…

机器学习 · 计算机科学 2018-04-02 Xingwei Cao , Xuyang Zhao , Qibin Zhao

We introduce Kernel Density Discrimination GAN (KDD GAN), a novel method for generative adversarial learning. KDD GAN formulates the training as a likelihood ratio optimization problem where the data distributions are written explicitly via…

机器学习 · 计算机科学 2021-07-14 Abdelhak Lemkhenter , Adam Bielski , Alp Eren Sari , Paolo Favaro

In this paper, we investigate the statistical convergence rate of a Bayesian low-rank tensor estimator. Our problem setting is the regression problem where a tensor structure underlying the data is estimated. This problem setting occurs in…

机器学习 · 统计学 2014-08-14 Taiji Suzuki

Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets. GANs are notoriuos for training difficulties and their dependence on arbitrary hyperparameters. One recent…

机器学习 · 计算机科学 2019-10-03 Thomas Pinetz , Daniel Soukup , Thomas Pock

Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they…

机器学习 · 统计学 2017-02-28 Shakir Mohamed , Balaji Lakshminarayanan

Many engineering problems require the prediction of realization-to-realization variability or a refined description of modeled quantities. In that case, it is necessary to sample elements from unknown high-dimensional spaces with possibly…

机器学习 · 统计学 2022-01-05 Malik Hassanaly , Andrew Glaws , Karen Stengel , Ryan N. King

A deep generative model yields an implicit estimator for the unknown distribution or density function of the observation. This paper investigates some statistical properties of the implicit density estimator pursued by VAE-type methods from…

统计理论 · 数学 2024-02-09 Hyeok Kyu Kwon , Minwoo Chae

Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many techniques in machine…

机器学习 · 计算机科学 2018-07-02 Samuel A. Barnett

Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and…

机器学习 · 统计学 2017-11-09 Yunus Saatchi , Andrew Gordon Wilson

GANs excel at learning high dimensional distributions, but they can update generator parameters in directions that do not correspond to the steepest descent direction of the objective. Prominent examples of problematic update directions…

机器学习 · 计算机科学 2018-06-08 Calvin Seward , Thomas Unterthiner , Urs Bergmann , Nikolay Jetchev , Sepp Hochreiter

We introduce the Probabilistic Generative Adversarial Network (PGAN), a new GAN variant based on a new kind of objective function. The central idea is to integrate a probabilistic model (a Gaussian Mixture Model, in our case) into the GAN…

机器学习 · 计算机科学 2017-08-08 Hamid Eghbal-zadeh , Gerhard Widmer

Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill-understood. In this work, we attempt to analyze generative…

机器学习 · 计算机科学 2018-09-13 Shuang Liu , Kamalika Chaudhuri

Generative models based on latent variables, such as generative adversarial networks (GANs) and variational auto-encoders (VAEs), have gained lots of interests due to their impressive performance in many fields. However, many data such as…

机器学习 · 统计学 2024-09-30 Yixuan Qiu , Qingyi Gao , Xiao Wang