English
Related papers

Related papers: Compressing Heavy-Tailed Weight Matrices for Non-V…

200 papers

We propose and analyze a new estimator of the covariance matrix that admits strong theoretical guarantees under weak assumptions on the underlying distribution, such as existence of moments of only low order. While estimation of covariance…

Statistics Theory · Mathematics 2018-01-17 Stanislav Minsker , Xiaohan Wei

Unraveling the reasons behind the remarkable success and exceptional generalization capabilities of deep neural networks presents a formidable challenge. Recent insights from random matrix theory, specifically those concerning the spectral…

Machine Learning · Statistics 2023-04-10 Xuanzhe Xiao , Zeng Li , Chuanlong Xie , Fengwei Zhou

Explaining the surprising generalization performance of deep neural networks is an active and important line of research in theoretical machine learning. Influential work by Arora et al. (ICML'18) showed that, noise stability properties of…

Machine Learning · Computer Science 2021-07-02 Allan Grønlund , Mikael Høgsgaard , Lior Kamma , Kasper Green Larsen

Neural network compression has been an increasingly important subject, not only due to its practical relevance, but also due to its theoretical implications, as there is an explicit connection between compressibility and generalization…

Machine Learning · Statistics 2024-02-13 Yijun Wan , Melih Barsbey , Abdellatif Zaidi , Umut Simsekli

We discuss non-Gaussian random matrices whose elements are random variables with heavy-tailed probability distributions. In probability theory heavy tails of the distributions describe rare but violent events which usually have dominant…

Mathematical Physics · Physics 2009-11-08 Z. Burda , J. Jurkiewicz

In the study of heavy tail data, several models have been introduced. If the interest is in the tail of the distribution, block maxima or excess over thresholds are the typical approaches, wasting relevant information in the bulk of the…

Methodology · Statistics 2026-02-10 Luis E. Nieto-Barajas

Neural network compression techniques have become increasingly popular as they can drastically reduce the storage and computation requirements for very large networks. Recent empirical studies have illustrated that even simple pruning…

Machine Learning · Statistics 2021-06-08 Melih Barsbey , Milad Sefidgaran , Murat A. Erdogdu , Gaël Richard , Umut Şimşekli

We offer a survey of recent results on covariance estimation for heavy-tailed distributions. By unifying ideas scattered in the literature, we propose user-friendly methods that facilitate practical implementation. Specifically, we…

Methodology · Statistics 2019-03-12 Yuan Ke , Stanislav Minsker , Zhao Ren , Qiang Sun , Wen-Xin Zhou

We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in [26], to address limitations of the standard Gaussian prior. It has been proved in [26] that, as the number…

Machine Learning · Statistics 2026-05-14 Nicola Apollonio , Giovanni Franzina , Giovanni Luca Torrisi

Modelling non-homogeneous and multi-component data is a problem that challenges scientific researchers in several fields. In general, it is not possible to find a simple and closed form probabilistic model to describe such data. That is why…

Methodology · Statistics 2017-12-27 Nehla Debbabi , Marie Kratz , Mamadou Mboup

Deep nets generalize well despite having more parameters than the number of training samples. Recent works try to give an explanation using PAC-Bayes and Margin-based analyses, but do not as yet result in sample complexity bounds better…

Machine Learning · Computer Science 2018-11-28 Sanjeev Arora , Rong Ge , Behnam Neyshabur , Yi Zhang

We consider a model for multivariate data with heavy-tailed marginal distributions and a Gaussian dependence structure. The different marginals in the model are allowed to have non-identical tail behavior in contrast to most popular…

Methodology · Statistics 2023-05-23 Bikramjit Das

The inputs and/or outputs of some neural nets are weight matrices of other neural nets. Indirect encodings or end-to-end compression of weight matrices could help to scale such approaches. Our goal is to open a discussion on this topic,…

Machine Learning · Computer Science 2022-01-03 Kazuki Irie , Jürgen Schmidhuber

We study an unconventional chiral random matrix model with a heavy-tailed probabilistic weight. The model is shown to exhibit chiral symmetry breaking with no bilinear condensate, in analogy to the Stern phase of QCD. We solve the model…

High Energy Physics - Theory · Physics 2016-05-31 Takuya Kanazawa

Despite the successes of probabilistic models based on passing noise through neural networks, recent work has identified that such methods often fail to capture tail behavior accurately, unless the tails of the base distribution are…

Machine Learning · Statistics 2023-06-16 Feynman Liang , Liam Hodgkinson , Michael W. Mahoney

We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an…

Machine Learning · Computer Science 2019-05-21 Cenk Baykal , Lucas Liebenwein , Igor Gilitschenski , Dan Feldman , Daniela Rus

Risk assessment for rare events is essential for understanding systemic stability in complex systems. As rare events are typically highly correlated, it is important to study heavy-tailed multivariate distributions of the relevant…

Statistical Finance · Quantitative Finance 2025-12-02 Efstratios Manolakis , Anton J. Heckens , Benjamin Köhler , Thomas Guhr

We consider a multivariate heavy-tailed stochastic volatility model and analyze the large-sample behavior of its sample covariance matrix. We study the limiting behavior of its entries in the infinite-variance case and derive results for…

Probability · Mathematics 2016-05-10 Anja Janßen , Thomas Mikosch , Mohsen Rezapour , Xiaolei Xie

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

We consider deep neural networks in a Bayesian framework with a prior distribution sampling the network weights at random. Following a recent idea of Agapiou and Castillo (2023), who show that heavy-tailed prior distributions achieve…

Machine Learning · Statistics 2025-04-16 Ismaël Castillo , Paul Egels
‹ Prev 1 2 3 10 Next ›