English
Related papers

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

200 papers

Generative adversarial networks (GANs) have emerged as a powerful tool for generating high-fidelity data. However, the main bottleneck of existing approaches is the lack of supervision on the generator training, which often results in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Baoren Xiao , Hao Ni , Weixin Yang

Auxiliary Classifier GANs (AC-GANs) are widely used conditional generative models and are capable of generating high-quality images. Previous work has pointed out that AC-GAN learns a biased distribution. To remedy this, Twin Auxiliary…

Computer Vision and Pattern Recognition · Computer Science 2020-06-16 Ligong Han , Anastasis Stathopoulos , Tao Xue , Dimitris Metaxas

In this work, we generalize semi-supervised generative adversarial networks (GANs) from classification problems to regression problems. In the last few years, the importance of improving the training of neural networks using semi-supervised…

Machine Learning · Computer Science 2019-09-05 Greg Olmschenk , Zhigang Zhu , Hao Tang

Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. The main aim of theoretical guarantees on the subject is…

Machine Learning · Statistics 2025-05-21 Dimitri Meunier , Zhu Li , Arthur Gretton , Samory Kpotufe

The number of credit card fraud has been growing as technology grows and people can take advantage of it. Therefore, it is very important to implement a robust and effective method to detect such frauds. The machine learning algorithms are…

Machine Learning · Computer Science 2022-06-14 Sairamvinay Vijayaraghavan , Terry Guan , Jason , Song

This work presents the first statistical performance guarantees for group-invariant generative models. Many real data, such as images and molecules, are invariant to certain group symmetries, which can be taken advantage of to learn more…

Machine Learning · Statistics 2025-03-12 Ziyu Chen , Markos A. Katsoulakis , Luc Rey-Bellet , Wei Zhu

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

Machine Learning · Computer Science 2026-05-12 Rajdeep Haldar , Lantao Mei , Guang Lin , Yue Xing , Qifan Song

This article investigates the approximation quality achievable for biobjective minimization problems with respect to the Pareto cone by solutions that are (approximately) optimal with respect to larger ordering cones. When simultaneously…

Optimization and Control · Mathematics 2021-09-22 Arne Herzel , Stephan Helfrich , Stefan Ruzika , Clemens Thielen

We investigate the use of parametrized families of information-theoretic measures to generalize the loss functions of generative adversarial networks (GANs) with the objective of improving performance. A new generator loss function, called…

Machine Learning · Computer Science 2021-08-12 Himesh Bhatia , William Paul , Fady Alajaji , Bahman Gharesifard , Philippe Burlina

We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific…

Machine Learning · Computer Science 2021-08-02 Sakshi Varshney , Vinay Kumar Verma , Srijith P K , Lawrence Carin , Piyush Rai

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…

Machine Learning · Computer Science 2022-06-20 Jeremiah Birrell , Markos A. Katsoulakis , Luc Rey-Bellet , Wei Zhu

Generative adversarial network (GAN) is a minimax game between a generator mimicking the true model and a discriminator distinguishing the samples produced by the generator from the real training samples. Given an unconstrained…

Machine Learning · Computer Science 2018-10-30 Farzan Farnia , David Tse

Generative Adversarial Networks (GANs) are powerful Machine Learning models capable of generating fully synthetic samples of a desired phenomenon with a high resolution. Despite their success, the training process of a GAN is highly…

Machine Learning · Computer Science 2022-09-07 Ángel González-Prieto , Alberto Mozo , Edgar Talavera , Sandra Gómez-Canaval

Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…

Machine Learning · Computer Science 2020-01-10 Yihao Feng , Lihong Li , Qiang Liu

In this paper we empirically evaluate biased methods for alpha-divergence minimization. In particular, we focus on how the bias affects the final solutions found, and how this depends on the dimensionality of the problem. We find that (i)…

Machine Learning · Computer Science 2021-05-17 Tomas Geffner , Justin Domke

This paper provides a more rigorous look at Relativistic Generative Adversarial Networks (RGANs). We prove that the objective function of the discriminator is a statistical divergence for any concave function $f$ with minimal properties…

Machine Learning · Computer Science 2019-01-10 Alexia Jolicoeur-Martineau

Generative adversarial networks (GANs) have enjoyed much success in learning high-dimensional distributions. Learning objectives approximately minimize an $f$-divergence ($f$-GANs) or an integral probability metric (Wasserstein GANs)…

Machine Learning · Computer Science 2020-06-19 Jiaming Song , Stefano Ermon

This paper gives upper and lower bounds on the minimum error probability of Bayesian $M$-ary hypothesis testing in terms of the Arimoto-R\'enyi conditional entropy of an arbitrary order $\alpha$. The improved tightness of these bounds over…

Information Theory · Computer Science 2017-12-06 Igal Sason , Sergio Verdú

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…

Machine Learning · Computer Science 2018-06-08 Calvin Seward , Thomas Unterthiner , Urs Bergmann , Nikolay Jetchev , Sepp Hochreiter

We apply the PAC-Bayes theory to the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable generalization guarantees (PAC-bounds) and explicit trade-off…

Machine Learning · Computer Science 2023-02-16 Michael Sucker , Peter Ochs