English
Related papers

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

200 papers

Generalization theory has been established for sparse deep neural networks under high-dimensional regime. Beyond generalization, parameter estimation is also important since it is crucial for variable selection and interpretability of deep…

Machine Learning · Statistics 2024-06-27 Dongya Wu , Xin Li

Data derived from remote sensing or numerical simulations often have a regular gridded structure and are large in volume, making it challenging to find accurate spatial models that can fill in missing grid cells or simulate the process…

Machine Learning · Statistics 2025-05-07 Sweta Rai , Douglas W. Nychka , Soutir Bandyopadhyay

We develop an econometric framework integrating heavy-tailed Student's $t$ distributions with behavioral probability weighting while preserving infinite divisibility. Using 432{,}752 observations across 86 assets (2004--2024), we…

Mathematical Finance · Quantitative Finance 2025-11-21 Akash Deep , Svetlozar T. Rachev , Frank J. Fabozzi

Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under $\ell_\infty$ attacks. To combat this problem, techniques like adversarial training have…

Machine Learning · Computer Science 2019-06-04 Emilio Rafael Balda , Arash Behboodi , Niklas Koep , Rudolf Mathar

Machine learning models have achieved human-level performance on various tasks. This success comes at a high cost of computation and storage overhead, which makes machine learning algorithms difficult to deploy on edge devices. Typically,…

Machine Learning · Computer Science 2021-11-12 Giuseppina Carannante , Dimah Dera , Ghulam Rasool , Nidhal C. Bouaynaya

We propose a variational tail bound for norms of random vectors under moment assumptions on their one-dimensional marginals. A simplified version of the bound that parametrizes the ``aggregating distribution'' using a certain pushforward of…

Probability · Mathematics 2026-02-02 Sohail Bahmani

Heavy-tailed distributions naturally occur in many real life problems. Unfortunately, it is typically not possible to compute inference in closed-form in graphical models which involve such heavy-tailed distributions. In this work, we…

Machine Learning · Computer Science 2011-03-22 Danny Bickson , Carlos Guestrin

Heavy-tailed metrics are common and often critical to product evaluation in the online world. While we may have samples large enough for Central Limit Theorem to kick in, experimentation is challenging due to the wide confidence interval of…

Applications · Statistics 2019-05-23 Jason , Wang , Pauline Burke

The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly reduced by dropping…

Machine Learning · Statistics 2022-11-10 Wenjing Yang , Ganghua Wang , Jie Ding , Yuhong Yang

Neural network (NN) designed for challenging machine learning tasks is in general a highly nonlinear mapping that contains massive variational parameters. High complexity of NN, if unbounded or unconstrained, might unpredictably cause…

Machine Learning · Computer Science 2025-05-23 Yong Qing , Ke Li , Peng-Fei Zhou , Shi-Ju Ran

Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices contributes to the…

Machine Learning · Computer Science 2025-01-27 Arash Behboodi , Gabriele Cesa

An expanded family of mixtures of multivariate power exponential distributions is introduced. While fitting heavy-tails and skewness has received much attention in the model-based clustering literature recently, we investigate the use of a…

Methodology · Statistics 2015-06-15 Utkarsh J. Dang , Ryan P. Browne , Paul D. McNicholas

The random variable $1+z_1+z_1z_2+\dots$ appears in many contexts and was shown by Kesten to exhibit a heavy tail distribution. We consider natural extensions of this variable and its associated recursion to $N \times N$ matrices either…

Statistical Mechanics · Physics 2021-08-03 Tristan Gautié , Jean-Philippe Bouchaud , Pierre Le Doussal

This article studies the infinite-width limit of deep feedforward neural networks whose weights are dependent, and modelled via a mixture of Gaussian distributions. Each hidden node of the network is assigned a nonnegative random variable…

Machine Learning · Statistics 2025-02-06 Hoil Lee , Fadhel Ayed , Paul Jung , Juho Lee , Hongseok Yang , François Caron

Even when neural networks are widely used in a large number of applications, they are still considered as black boxes and present some difficulties for dimensioning or evaluating their prediction error. This has led to an increasing…

Machine Learning · Statistics 2021-05-11 Pablo Morala , Jenny Alexandra Cifuentes , Rosa E. Lillo , Iñaki Ucar

We study the fundamental task of outlier-robust mean estimation for heavy-tailed distributions in the presence of sparsity. Specifically, given a small number of corrupted samples from a high-dimensional heavy-tailed distribution whose mean…

Data Structures and Algorithms · Computer Science 2022-11-30 Ilias Diakonikolas , Daniel M. Kane , Jasper C. H. Lee , Ankit Pensia

Deep neural network pruning and quantization techniques have demonstrated it is possible to achieve high levels of compression with surprisingly little degradation to test set accuracy. However, this measure of performance conceals…

Machine Learning · Computer Science 2021-09-07 Sara Hooker , Aaron Courville , Gregory Clark , Yann Dauphin , Andrea Frome

Over the last few decades power law distributions have been suggested as forming generative mechanisms in a variety of disparate fields, such as, astrophysics, criminology and database curation. However, fitting these heavy tailed…

Computation · Statistics 2014-08-26 Colin S. Gillespie

Score-based generative models (SGMs) have achieved remarkable empirical success, motivating their application to a broad range of data distributions. However, extending them to heavy-tailed targets remains a largely open problem. Although…

Machine Learning · Statistics 2026-05-15 Tiziano Fassina , Gabriel Cardoso , Sylvan Le Corff , Thomas Romary

We revisit the probabilistic construction of sparse random matrices where each column has a fixed number of nonzeros whose row indices are drawn uniformly at random. These matrices have a one-to-one correspondence with the adjacency…

Information Theory · Computer Science 2013-07-25 Bubacarr Bah , Jared Tanner