English
Related papers

Related papers: Approximate is Good Enough: Probabilistic Variants…

200 papers

Positive definite kernels and their associated Reproducing Kernel Hilbert Spaces provide a mathematically compelling and practically competitive framework for learning from data. In this paper we take the approximation theory point of view…

Machine Learning · Computer Science 2018-08-06 Mikhail Belkin

The classical perceptron rule provides a varying upper bound on the maximum margin, namely the length of the current weight vector divided by the total number of updates up to that time. Requiring that the perceptron updates its internal…

Machine Learning · Computer Science 2011-05-31 Constantinos Panagiotakopoulos , Petroula Tsampouka

Decision-theoretic troubleshooting is one of the areas to which Bayesian networks can be applied. Given a probabilistic model of a malfunctioning man-made device, the task is to construct a repair strategy with minimal expected cost. The…

Artificial Intelligence · Computer Science 2013-08-02 Václav Lín

To accelerate kernel methods, we propose a near input sparsity time algorithm for sampling the high-dimensional feature space implicitly defined by a kernel transformation. Our main contribution is an importance sampling method for…

Data Structures and Algorithms · Computer Science 2020-07-15 David P. Woodruff , Amir Zandieh

We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization,…

Machine Learning · Statistics 2025-10-15 Einar Urdshals , Edmund Lau , Jesse Hoogland , Stan van Wingerden , Daniel Murfet

Approximation theory is concerned with the ability to approximate functions by simpler and more easily calculated functions. The first question we ask in approximation theory concerns the {\it possibility of approximation}. Is the given…

Classical Analysis and ODEs · Mathematics 2007-05-23 Allan Pinkus

We introduce the concept of boundariness capturing the most efficient way of expressing a given element of a convex set as a probability mixture of its boundary elements. In other words, this number measures (without the need of any…

Quantum Physics · Physics 2014-09-01 Erkka Haapasalo , Michal Sedlak , Mario Ziman

Low-rank tensor approximations have shown great potential for uncertainty quantification in high dimensions, for example, to build surrogate models that can be used to speed up large-scale inference problems (Eigel et al., Inverse Problems…

Numerical Analysis · Mathematics 2020-11-30 Paul B. Rohrbach , Sergey Dolgov , Lars Grasedyck , Robert Scheichl

In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning. We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and…

Machine Learning · Computer Science 2020-10-27 Giambattista Parascandolo , Alexander Neitz , Antonio Orvieto , Luigi Gresele , Bernhard Schölkopf

We study a quantity called discrete layered entropy, which approximates the Shannon entropy within a logarithmic gap. Compared to the Shannon entropy, the discrete layered entropy is piecewise linear, approximates the expected length of the…

Information Theory · Computer Science 2026-01-27 Cheuk Ting Li

Generalized matrix approximation plays a fundamental role in many machine learning problems, such as CUR decomposition, kernel approximation, and matrix low rank approximation. Especially with today's applications involved in larger and…

Numerical Analysis · Computer Science 2016-09-09 Haishan Ye , Qiaoming Ye , Zhihua Zhang

We present a general framework for analyzing the complexity of subdivision-based algorithms whose tests are based on the sizes of regions and their distance to certain sets (often varieties) intrinsic to the problem under study. We call…

Symbolic Computation · Computer Science 2018-01-19 Michael Burr , Shuhong Gao , Elias Tsigaridas

Approximate algebraic structures play a defining role in arithmetic combinatorics and have found remarkable applications to basic questions in number theory and pseudorandomness. Here we study approximate representations of finite groups:…

Representation Theory · Mathematics 2010-10-01 Cristopher Moore , Alexander Russell

This paper addresses the problem of nearly optimal Vapnik--Chervonenkis dimension (VC-dimension) and pseudo-dimension estimations of the derivative functions of deep neural networks (DNNs). Two important applications of these estimations…

Machine Learning · Computer Science 2023-05-16 Yahong Yang , Haizhao Yang , Yang Xiang

Given a matrix $A$, a linear feasibility problem (of which linear classification is a special case) aims to find a solution to a primal problem $w: A^Tw > \textbf{0}$ or a certificate for the dual problem which is a probability distribution…

Optimization and Control · Mathematics 2016-02-01 Aaditya Ramdas , Javier Peña

The purpose of the paper is to provide a characterization of the error of the best polynomial approximation of composite functions in weighted spaces. Such a characterization is essential for the convergence analysis of numerical methods…

Numerical Analysis · Mathematics 2023-08-14 Luisa Fermo , Concetta Laurita , Maria Grazia Russo

There has been a lot of interest in sufficient dimension reduction (SDR) methodologies as well as nonlinear extensions in the statistics literature. In this note, we use classical results regarding metric spaces and positive definite…

Methodology · Statistics 2020-10-29 Youngjoo Cho , Debashis Ghosh

Invariance (defined in a general sense) has been one of the most effective priors for representation learning. Direct factorization of parametric models is feasible only for a small range of invariances, while regularization approaches,…

Machine Learning · Computer Science 2020-07-28 Yingyi Ma , Vignesh Ganapathiraman , Yaoliang Yu , Xinhua Zhang

Kernel methods give powerful, flexible, and theoretically grounded approaches to solving many problems in machine learning. The standard approach, however, requires pairwise evaluations of a kernel function, which can lead to scalability…

Machine Learning · Computer Science 2021-04-08 Danica J. Sutherland , Jeff Schneider

We derive fundamental lower bounds on the connectivity and the memory requirements of deep neural networks guaranteeing uniform approximation rates for arbitrary function classes in $L^2(\mathbb R^d)$. In other words, we establish a…

Machine Learning · Computer Science 2018-05-17 Helmut Bölcskei , Philipp Grohs , Gitta Kutyniok , Philipp Petersen