English
Related papers

Related papers: MIND: Monge Inception Distance for Generative Mode…

200 papers

We propose two new evaluation metrics to assess realness of generated images based on normalizing flows: a simpler and efficient flow-based likelihood distance (FLD) and a more exact dual-flow based likelihood distance (D-FLD). Because…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Pranav Jeevan , Neeraj Nixon , Amit Sethi

Deep generative models are powerful tools that have produced impressive results in recent years. These advances have been for the most part empirically driven, making it essential that we use high quality evaluation metrics. In this paper,…

Machine Learning · Statistics 2018-06-22 Shane Barratt , Rishi Sharma

The Wasserstein distance between mixing measures has come to occupy a central place in the statistical analysis of mixture models. This work proposes a new canonical interpretation of this distance and provides tools to perform inference on…

Statistics Theory · Mathematics 2024-09-10 Xin Bing , Florentina Bunea , Jonathan Niles-Weed

In the process of training a generative model, it becomes essential to measure the discrepancy between two high-dimensional probability distributions: the generative distribution and the ground-truth distribution of the observed dataset.…

Machine Learning · Statistics 2023-12-07 Seunghwan An , Sungchul Hong , Jong-June Jeon

Generative models are designed to address the data scarcity problem. Even with the exploding amount of data, due to computational advancements, some applications (e.g., health care, weather forecast, fault detection) still suffer from data…

Machine Learning · Computer Science 2024-05-07 Alireza Koochali , Maria Walch , Sankrutyayan Thota , Peter Schichtel , Andreas Dengel , Sheraz Ahmed

Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distribution is from the true data distribution. A recent advance…

Computer Vision and Pattern Recognition · Computer Science 2017-04-18 Felix Juefei-Xu , Vishnu Naresh Boddeti , Marios Savvides

Optimal transportation theory and the related $p$-Wasserstein distance ($W_p$, $p\geq 1$) are widely-applied in statistics and machine learning. In spite of their popularity, inference based on these tools has some issues. For instance, it…

Statistics Theory · Mathematics 2024-03-01 Yiming Ma , Hang Liu , Davide La Vecchia , Metthieu Lerasle

An important class of distance metrics proposed for training generative adversarial networks (GANs) is the integral probability metric (IPM), in which the neural net distance captures the practical GAN training via two neural networks. This…

Machine Learning · Computer Science 2018-11-06 Kaiyi Ji , Yingbin Liang

In terms of Generative Adversarial Networks (GANs), the information metric to discriminate the generative data from the real data, lies in the key point of generation efficiency, which plays an important role in GAN-based applications,…

Machine Learning · Computer Science 2021-01-08 Rui She , Pingyi Fan

Measuring Mutual Information (MI) between high-dimensional, continuous, random variables from observed samples has wide theoretical and practical applications. Recent work, MINE (Belghazi et al. 2018), focused on estimating tight…

Machine Learning · Computer Science 2019-05-28 Xiao Lin , Indranil Sur , Samuel A. Nastase , Ajay Divakaran , Uri Hasson , Mohamed R. Amer

Imbalanced classification remains a pervasive challenge in machine learning, particularly when minority samples are too scarce to provide a robust discriminative boundary. In such extreme scenarios, conventional models often suffer from…

Machine Learning · Computer Science 2026-04-29 Hongfei Wu , Ruijian Han , Yancheng Yuan

Most approaches to deep neural network compression via pruning either evaluate a filter's importance using its weights or optimize an alternative objective function with sparsity constraints. While these methods offer a useful way to…

Machine Learning · Computer Science 2020-03-20 Madan Ravi Ganesh , Jason J. Corso , Salimeh Yasaei Sekeh

We present a unifying view on various statistical estimation techniques including penalization, variational and thresholding methods. These estimators will be analyzed in the context of statistical linear inverse problems including…

Methodology · Statistics 2022-03-11 Markus Haltmeier , Housen Li , Axel Munk

We present the Membership Inference Test Demonstrator, to emphasize the need for more transparent machine learning training processes. MINT is a technique for experimentally determining whether certain data has been used during the training…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Daniel DeAlcala , Aythami Morales , Julian Fierrez , Gonzalo Mancera , Ruben Tolosana , Ruben Vera-Rodriguez

Generative modelling is often cast as minimizing a similarity measure between a data distribution and a model distribution. Recently, a popular choice for the similarity measure has been the Wasserstein metric, which can be expressed in the…

Machine Learning · Computer Science 2019-10-10 Anton Mallasto , Guido Montúfar , Augusto Gerolin

The training and test data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the test samples are drawn from a distribution that is sufficiently far away from that of the…

Machine Learning · Computer Science 2021-12-14 Yinan Wang , Wenbo Sun , Jionghua "Judy" Jin , Zhenyu "James" Kong , Xiaowei Yue

Generative Adversarial Networks have surprising ability for generating sharp and realistic images, though they are known to suffer from the so-called mode collapse problem. In this paper, we propose a new GAN variant called Mixture Density…

Machine Learning · Computer Science 2018-11-30 Hamid Eghbal-zadeh , Werner Zellinger , Gerhard Widmer

We define a novel class of distances between statistical multivariate distributions by modeling an optimal transport problem on their marginals with respect to a ground distance defined on their conditionals. These new distances are metrics…

Machine Learning · Computer Science 2020-11-03 Frank Nielsen , Ke Sun

We propose a test of independence of two multivariate random vectors, given a sample from the underlying population. Our approach, which we call MINT, is based on the estimation of mutual information, whose decomposition into joint and…

Methodology · Statistics 2017-11-20 Thomas B. Berrett , Richard J. Samworth

Mixed-integer linear programming (MILP) is a powerful tool for addressing a wide range of real-world problems, but it lacks a clear structure for comparing instances. A reliable similarity metric could establish meaningful relationships…

Machine Learning · Computer Science 2025-07-16 Gwen Maudet , Grégoire Danoy
‹ Prev 1 4 5 6 7 8 10 Next ›