English
Related papers

Related papers: $\alpha$-GAN: Convergence and Estimation Guarantee…

200 papers

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…

Statistics Theory · Mathematics 2020-01-14 Ananya Uppal , Shashank Singh , Barnabás Póczos

We propose studying GAN training dynamics as regret minimization, which is in contrast to the popular view that there is consistent minimization of a divergence between real and generated distributions. We analyze the convergence of GAN…

Artificial Intelligence · Computer Science 2017-12-12 Naveen Kodali , Jacob Abernethy , James Hays , Zsolt Kira

We relate the minimax game of generative adversarial networks (GANs) to finding the saddle points of the Lagrangian function for a convex optimization problem, where the discriminator outputs and the distribution of generator outputs play…

Machine Learning · Computer Science 2018-02-07 Xu Chen , Jiang Wang , Hao Ge

The empirical success of Generative Adversarial Networks (GANs) caused an increasing interest in theoretical research. The statistical literature is mainly focused on Wasserstein GANs and generalizations thereof, which especially allow for…

Statistics Theory · Mathematics 2024-07-30 Lea Kunkel , Mathias Trabs

We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function. We estimate the appropriate hinge…

Machine Learning · Computer Science 2017-05-24 Ruohan Wang , Antoine Cully , Hyung Jin Chang , Yiannis Demiris

This paper establishes the functional convergence of the Extreme Nelson--Aalen and Extreme Kaplan--Meier estimators, which are designed to capture the heavy-tailed behaviour of censored losses. The resulting limit representations can be…

Methodology · Statistics 2024-08-22 Martin Bladt , Christoffer Øhlenschlæger

This work addresses the synthesis of optimal feedback control laws via machine learning. In particular, the Averaged Feedback Learning Scheme (AFLS) and a data driven method are considered. Hypotheses for each method ensuring the…

Optimization and Control · Mathematics 2025-05-28 Karl Kunisch , Donato Vásquez-Varas

Feature alignment methods are used in many scientific disciplines for data pooling, annotation, and comparison. As an instance of a permutation learning problem, feature alignment presents significant statistical and computational…

Statistics Theory · Mathematics 2023-11-23 Yanjun Han , Philippe Rigollet , George Stepaniants

Generative adversarial networks (GANs) are often billed as "universal distribution learners", but precisely what distributions they can represent and learn is still an open question. Heavy-tailed distributions are prevalent in many…

Machine Learning · Computer Science 2021-01-25 Todd Huster , Jeremy E. J. Cohen , Zinan Lin , Kevin Chan , Charles Kamhoua , Nandi Leslie , Cho-Yu Jason Chiang , Vyas Sekar

We compare classification and regression tasks in an overparameterized linear model with Gaussian features. On the one hand, we show that with sufficient overparameterization all training points are support vectors: solutions obtained by…

Machine Learning · Computer Science 2021-10-15 Vidya Muthukumar , Adhyyan Narang , Vignesh Subramanian , Mikhail Belkin , Daniel Hsu , Anant Sahai

Class imbalance is an inherent problem in many machine learning classification tasks. This often leads to trained models that are unusable for any practical purpose. In this study we explore an unsupervised approach to address these…

Machine Learning · Computer Science 2021-08-20 Ademola Okerinde , Lior Shamir , William Hsu , Tom Theis , Nasik Nafi

In this work, we showed that the Implicit Update and Predictive Methods dynamics introduced in prior work satisfy last iterate convergence to a neighborhood around the optimum in overparameterized GANs, where the size of the neighborhood…

Machine Learning · Computer Science 2021-08-10 Elbert Du

The $f$-divergence is a fundamental notion that measures the difference between two distributions. In this paper, we study the problem of approximating the $f$-divergence between two Ising models, which is a generalization of recent work on…

Data Structures and Algorithms · Computer Science 2025-09-08 Weiming Feng , Yucheng Fu

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…

Machine Learning · Statistics 2021-01-15 Mikołaj Bińkowski , Danica J. Sutherland , Michael Arbel , Arthur Gretton

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

Recent years have seen a surge of interest in the algorithmic estimation of stochastic entropy production (EP) from trajectory data via machine learning. A crucial element of such algorithms is the identification of a loss function whose…

Statistical Mechanics · Physics 2024-01-22 Euijoon Kwon , Yongjoo Baek

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…

Statistics Theory · Mathematics 2018-10-30 Shashank Singh , Ananya Uppal , Boyue Li , Chun-Liang Li , Manzil Zaheer , Barnabás Póczos

We present a framework to understand GAN training as alternating density ratio estimation and approximate divergence minimization. This provides an interpretation for the mismatched GAN generator and discriminator objectives often used in…

Machine Learning · Computer Science 2016-12-09 Ben Poole , Alexander A. Alemi , Jascha Sohl-Dickstein , Anelia Angelova

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.…

Machine Learning · Computer Science 2018-05-23 Maziar Sanjabi , Jimmy Ba , Meisam Razaviyayn , Jason D. Lee

Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. In this paper, we propose a novel training pipeline to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Haozhe Liu , Bing Li , Haoqian Wu , Hanbang Liang , Yawen Huang , Yuexiang Li , Bernard Ghanem , Yefeng Zheng
‹ Prev 1 3 4 5 6 7 10 Next ›