中文
相关论文

相关论文: Rates of convergence for nonparametric estimation …

200 篇论文

Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated…

机器学习 · 统计学 2018-02-23 R Devon Hjelm , Athul Paul Jacob , Tong Che , Adam Trischler , Kyunghyun Cho , Yoshua Bengio

One of the training strategies of generative models is to minimize the Jensen--Shannon divergence between the model distribution and the data distribution. Since data distribution is unknown, generative adversarial networks (GANs) formulate…

机器学习 · 计算机科学 2023-02-22 Hiroki Naganuma , Hideaki Iiduka

Generative Adversarial Networks (GANs) have become a very popular tool for implicitly learning high-dimensional probability distributions. Several improvements have been made to the original GAN formulation to address some of its…

计算机视觉与模式识别 · 计算机科学 2019-11-11 Parimala Kancharla , Sumohana S. Channappayya

Estimation of Distribution Algorithms (EDAs) require flexible probability models that can be efficiently learned and sampled. Generative Adversarial Networks (GAN) are generative neural networks which can be trained to implicitly model the…

神经与进化计算 · 计算机科学 2016-08-09 Malte Probst

Generative adversarial networks (GAN) approximate a target data distribution by jointly optimizing an objective function through a "two-player game" between a generator and a discriminator. Despite their empirical success, however, two very…

机器学习 · 计算机科学 2017-05-30 Shuang Liu , Olivier Bousquet , Kamalika Chaudhuri

Distributional causal inference requires estimating not only average treatment effects but also interventional outcome distributions, including quantiles, tail risks, and policy-dependent uncertainty. As a method for distributional causal…

统计理论 · 数学 2026-05-12 Shu Tamano , Masaaki Imaizumi

We propose a generative model that achieves minimax-optimal convergence rates for estimating probability distributions supported on unknown low-dimensional manifolds. Building on Fefferman's solution to the geometric Whitney problem, our…

统计理论 · 数学 2025-06-25 Arthur Stéphanovitch

We investigate statistical properties of a likelihood approach to nonparametric estimation of a singular distribution using deep generative models. More specifically, a deep generative model is used to model high-dimensional data that are…

机器学习 · 统计学 2023-03-29 Minwoo Chae , Dongha Kim , Yongdai Kim , Lizhen Lin

Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport (OT). Generative adversarial networks (GANs) are powerful generative models which have been successfully…

机器学习 · 计算机科学 2019-06-25 Jacob Leygonie , Jennifer She , Amjad Almahairi , Sai Rajeswar , Aaron Courville

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

Robust scatter estimation is a fundamental task in statistics. The recent discovery on the connection between robust estimation and generative adversarial nets (GANs) by Gao et al. (2018) suggests that it is possible to compute depth-like…

机器学习 · 计算机科学 2019-03-06 Chao Gao , Yuan Yao , Weizhi Zhu

Generative adversarial networks (GANs), a class of distribution-learning methods based on a two-player game between a generator and a discriminator, can generally be formulated as a minmax problem based on the variational representation of…

机器学习 · 计算机科学 2022-06-20 Jeremiah Birrell , Markos A. Katsoulakis , Luc Rey-Bellet , Wei Zhu

We present a novel method and analysis to train generative adversarial networks (GAN) in a stable manner. As shown in recent analysis, training is often undermined by the probability distribution of the data being zero on neighborhoods of…

计算机视觉与模式识别 · 计算机科学 2019-09-18 Simon Jenni , Paolo Favaro

Generative adversarial networks constitute a powerful approach to generative modeling. While generated samples often are indistinguishable from real data, there is no guarantee that they will follow the true data distribution. For…

机器学习 · 统计学 2024-09-09 Philipp Pilar , Niklas Wahlström

Studied here are Wasserstein generative adversarial networks (WGANs) with GroupSort neural networks as their discriminators. It is shown that the error bound of the approximation for the target distribution depends on the width and depth…

机器学习 · 计算机科学 2023-07-03 Yihang Gao , Michael K. Ng , Mingjie Zhou

Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the…

机器学习 · 计算机科学 2020-04-29 Shufei Zhang , Zhuang Qian , Kaizhu Huang , Jimin Xiao , Yuan He

Generative Adversarial Networks (GANs) are one of the most practical methods for learning data distributions. A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions.…

机器学习 · 计算机科学 2018-05-23 Maziar Sanjabi , Jimmy Ba , Meisam Razaviyayn , Jason D. Lee

Generative Adversarial Nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often not stable. While this is…

计算机视觉与模式识别 · 计算机科学 2018-03-30 Ishan Deshpande , Ziyu Zhang , Alexander Schwing

We introduce a novel framework for adversarial training where the target distribution is annealed between the uniform distribution and the data distribution. We posited a conjecture that learning under continuous annealing in the…

机器学习 · 统计学 2017-05-23 Arash Mehrjou , Bernhard Schölkopf , Saeed Saremi

Generative Adversarial Networks (GANs) are popular and successful generative models. Despite their success, optimization is notoriously challenging. In this work, we explain the success and limitations of GANs by casting them as Bayesian…

机器学习 · 计算机科学 2026-02-03 Maurizio Filippone , Marius P. Linhard