English
Related papers

Related papers: Global Convergence to the Equilibrium of GANs usin…

200 papers

We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example of very deep architectures, their training constitutes a challenging optimization problem due notably to…

Machine Learning · Computer Science 2025-07-22 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

Generative adversarial networks have been very successful in generative modeling, however they remain relatively challenging to train compared to standard deep neural networks. In this paper, we propose new visualization techniques for the…

Machine Learning · Computer Science 2020-04-28 Hugo Berard , Gauthier Gidel , Amjad Almahairi , Pascal Vincent , Simon Lacoste-Julien

Many applications in machine learning can be framed as minimization problems and solved efficiently using gradient-based techniques. However, recent applications of generative models, particularly GANs, have triggered interest in solving…

Machine Learning · Computer Science 2021-03-24 Paulina Grnarova , Yannic Kilcher , Kfir Y. Levy , Aurelien Lucchi , Thomas Hofmann

In this work, we consider smooth unconstrained optimization problems and we deal with the class of gradient methods with momentum, i.e., descent algorithms where the search direction is defined as a linear combination of the current…

Optimization and Control · Mathematics 2025-12-04 Matteo Lapucci , Giampaolo Liuzzi , Stefano Lucidi , Davide Pucci , Marco Sciandrone

The conventional understanding of adversarial training in generative adversarial networks (GANs) is that the discriminator is trained to estimate a divergence, and the generator learns to minimize this divergence. We argue that despite the…

Machine Learning · Statistics 2023-08-09 Mingxuan Yi , Zhanxing Zhu , Song Liu

To improve the performance of classical generative adversarial network (GAN), Wasserstein generative adversarial networks (W-GAN) was developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1…

Computer Vision and Pattern Recognition · Computer Science 2020-09-01 Byeongsu Sim , Gyutaek Oh , Jeongsol Kim , Chanyong Jung , Jong Chul Ye

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…

Computer Vision and Pattern Recognition · Computer Science 2019-11-11 Parimala Kancharla , Sumohana S. Channappayya

Generative Adversarial Networks (GANs) were intuitively and attractively explained under the perspective of game theory, wherein two involving parties are a discriminator and a generator. In this game, the task of the discriminator is to…

Machine Learning · Computer Science 2017-11-07 Trung Le , Tu Dinh Nguyen , Dinh Phung

The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks. A standard multi-task learning objective is to minimize the average loss across all…

Machine Learning · Computer Science 2024-02-22 Bo Liu , Xingchao Liu , Xiaojie Jin , Peter Stone , Qiang Liu

Recent work has shown local convergence of GAN training for absolutely continuous data and generator distributions. In this paper, we show that the requirement of absolute continuity is necessary: we describe a simple yet prototypical…

Machine Learning · Computer Science 2018-08-01 Lars Mescheder , Andreas Geiger , Sebastian Nowozin

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

Machine Learning · Computer Science 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian

The analysis of parametric and non-parametric uncertainties of very large dynamical systems requires the construction of a stochastic model of said system. Linear approaches relying on random matrix theory and principal componant analysis…

Machine Learning · Statistics 2023-02-02 Hamza Boukraichi , Nissrine Akkari , Fabien Casenave , David Ryckelynck

This paper proposes a new theoretical lens to view Wasserstein generative adversarial networks (WGANs). To minimize the Wasserstein-1 distance between the true data distribution and our estimate of it, we derive a distribution-dependent…

Machine Learning · Statistics 2025-02-05 Zachariah Malik , Yu-Jui Huang

We consider the maximum mean discrepancy ($\mathrm{MMD}$) GAN problem and propose a parametric kernelized gradient flow that mimics the min-max game in gradient regularized $\mathrm{MMD}$ GAN. We show that this flow provides a descent…

Machine Learning · Computer Science 2020-11-05 Youssef Mroueh , Truyen Nguyen

Non-uniform blur, mainly caused by camera shake and motions of multiple objects, is one of the most common causes of image quality degradation. However, the traditional blind deblurring methods based on blur kernel estimation do not perform…

Image and Video Processing · Electrical Eng. & Systems 2019-12-05 Shuai Zheng , Zhenfeng Zhu , Jian Cheng , Yandong Guo , Yao Zhao

The two-timescale gradient descent-ascent (GDA) is a canonical gradient algorithm designed to find Nash equilibria in min-max games. We analyze the two-timescale GDA by investigating the effects of learning rate ratios on convergence…

Optimization and Control · Mathematics 2025-10-13 Jing An , Jianfeng Lu

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

Machine Learning · Computer Science 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

Under mild regularity conditions, gradient-based methods converge globally to a critical point in the single-loss setting. This is known to break down for vanilla gradient descent when moving to multi-loss optimization, but can we hope to…

Optimization and Control · Mathematics 2021-01-19 Alistair Letcher

Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise…

Quantum Physics · Physics 2024-08-14 Kaiming Bian , Shitao Zhang , Fei Meng , Wen Zhang , Oscar Dahlsten
‹ Prev 1 3 4 5 6 7 10 Next ›