English
Related papers

Related papers: Sobolev GAN

200 papers

We introduce a notion of "gradient at a given scale" of functions defined on a metric measure space. We then use it to define Sobolev inequalities at large scale and we prove their invariance under large-scale equivalence (maps that…

Metric Geometry · Mathematics 2007-05-23 Romain Tessera

The true distribution parameterizations of commonly used image datasets are inaccessible. Rather than designing metrics for feature spaces with unknown characteristics, we propose to measure GAN performance by evaluating on explicitly…

Machine Learning · Computer Science 2018-12-31 Shayne O'Brien , Matt Groh , Abhimanyu Dubey

Optimal higher-order Sobolev type embeddings are shown to follow via isoperimetric inequalities. This establishes a higher-order analogue of a well-known link between first-order Sobolev embeddings and isoperimetric inequalities. Sobolev…

Functional Analysis · Mathematics 2013-11-04 Andrea Cianchi , Luboš Pick , Lenka Slavíková

This paper studies Hoeffding's inequality for Markov chains under the generalized concentrability condition defined via integral probability metric (IPM). The generalized concentrability condition establishes a framework that interpolates…

Machine Learning · Statistics 2023-10-06 Hao Chen , Abhishek Gupta , Yin Sun , Ness Shroff

Gradient information is widely useful and available in applications, and is therefore natural to include in the training of neural networks. Yet little is known theoretically about the impact of Sobolev training -- regression with both…

Machine Learning · Statistics 2025-11-06 Katharine E Fisher , Matthew TC Li , Youssef Marzouk , Timo Schorlepp

As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss is using feature map…

Machine Learning · Computer Science 2017-11-15 Gongze Cao , Yezhou Yang , Jie Lei , Cheng Jin , Yang Liu , Mingli Song

This paper presents a kernel-based discriminative learning framework on probability measures. Rather than relying on large collections of vectorial training examples, our framework learns using a collection of probability distributions that…

Machine Learning · Statistics 2013-01-15 Krikamol Muandet , Kenji Fukumizu , Francesco Dinuzzo , Bernhard Schölkopf

We show that the convolution of a compactly supported measure on $\mathbb{R}$ with a Gaussian measure satisfies a logarithmic Sobolev inequality (LSI). We use this result to give a new proof of a classical result in random matrix theory…

Probability · Mathematics 2014-11-07 David Zimmermann

We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,\Gamma)$-divergences, we prove a new infimal subadditivity principle showing that,…

Machine Learning · Statistics 2026-04-03 Panagiota Birmpa , Eric Joseph Hall

We show in this note that the Sobolev Discrepancy introduced in Mroueh et al in the context of generative adversarial networks, is actually the weighted negative Sobolev norm $||.||_{\dot{H}^{-1}(\nu_q)}$, that is known to linearize the…

Machine Learning · Computer Science 2018-05-17 Youssef Mroueh

Robustness to adversarial attacks is an important concern due to the fragility of deep neural networks to small perturbations and has received an abundance of attention in recent years. Distributionally Robust Optimization (DRO), a…

Machine Learning · Statistics 2020-06-09 Hisham Husain

We prove new concentration estimates for random variables that are functionals of a Poisson measure defined on a general measure space. Our results are specifically adapted to geometric applications, and are based on a pervasive use of a…

Probability · Mathematics 2015-04-14 Sascha Bachmann , Giovanni Peccati

An unavoidable task in quantum information processing is how to obtain data about the state of an individual system by suitable measurements. Informationally complete measurements are relevant in quantum state tomography, quantum…

Quantum Physics · Physics 2014-08-19 Alexey E. Rastegin

The concentration of empirical measures is studied for dependent data, whose joint distribution satisfies Poincar\'{e}-type or logarithmic Sobolev inequalities. The general concentration results are then applied to spectral empirical…

Statistics Theory · Mathematics 2010-11-30 S. G. Bobkov , F. Götze

A classic inferential statistical problem is the goodness-of-fit (GOF) test. Such a test can be challenging when the hypothesized parametric model has an intractable likelihood and its distributional form is not available. Bayesian methods…

Machine Learning · Statistics 2023-11-13 Forough Fazeli-Asl , Michael Minyi Zhang , Lizhen Lin

We derive sufficient conditions for a probability measure on a finite product space (a spin system) to satisfy a (modified) logarithmic Sobolev inequality. We establish these conditions for various examples, such as the (vertex-weighted)…

Probability · Mathematics 2020-05-15 Holger Sambale , Arthur Sinulis

In standard generative adversarial network (SGAN), the discriminator estimates the probability that the input data is real. The generator is trained to increase the probability that fake data is real. We argue that it should also…

Machine Learning · Computer Science 2018-09-11 Alexia Jolicoeur-Martineau

While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work…

Machine Learning · Computer Science 2019-07-02 Yu Bai , Tengyu Ma , Andrej Risteski

A Distributional (Single) Index Model (DIM) is a semi-parametric model for distributional regression, that is, estimation of conditional distributions given covariates. The method is a combination of classical single index models for the…

Methodology · Statistics 2022-08-04 Alexander Henzi , Gian-Reto Kleger , Johanna F. Ziegel

Conformal prediction is a powerful distribution-free framework for constructing prediction sets with coverage guarantees. Classical methods, such as split conformal prediction, provide marginal coverage, ensuring that the prediction set…

Machine Learning · Computer Science 2025-08-01 Konstantina Bairaktari , Jiayun Wu , Zhiwei Steven Wu