English
Related papers

Related papers: Generalization error of minimum weighted norm and …

200 papers

Nonlinear interpolants have been shown useful for the verification of programs and hybrid systems in contexts of theorem proving, model checking, abstract interpretation, etc. The underlying synthesis problem, however, is challenging and…

Logic in Computer Science · Computer Science 2019-08-29 Mingshuai Chen , Jian Wang , Jie An , Bohua Zhan , Deepak Kapur , Naijun Zhan

We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width $k$ and input dimension $d$ are large and proportional. We provide an effective theory for approximating the Bayes-optimal…

Machine Learning · Statistics 2025-04-02 Jean Barbier , Francesco Camilli , Minh-Toan Nguyen , Mauro Pastore , Rudy Skerk

The error between appropriately smooth functions and their radial basis function interpolants, as the interpolation points fill out a bounded domain in R^d, is a well studied artifact. In all of these cases, the analysis takes place in a…

Numerical Analysis · Mathematics 2007-12-02 R. A. Brownlee

Convergence rates for $L_2$ approximation in a Hilbert space $H$ are a central theme in numerical analysis. The present work is inspired by Schaback (Math. Comp., 1999), who showed, in the context of best pointwise approximation for radial…

Numerical Analysis · Mathematics 2024-10-01 Ian H. Sloan , Vesa Kaarnioja

The problem of resolving the fine details of a signal from its coarse scale measurements or, as it is commonly referred to in the literature, the super-resolution problem arises naturally in engineering and physics in a variety of settings.…

Information Theory · Computer Science 2015-04-14 Tamir Bendory , Shai Dekel , Arie Feuer

Kernel methods are widely used in machine learning, especially for classification problems. However, the theoretical analysis of kernel classification is still limited. This paper investigates the statistical performances of kernel…

Statistics Theory · Mathematics 2024-02-05 Jianfa Lai , Zhifan Li , Dongming Huang , Qian Lin

Distributed learning is an effective way to analyze big data. In distributed regression, a typical approach is to divide the big data into multiple blocks, apply a base regression algorithm on each of them, and then simply average the…

Machine Learning · Computer Science 2017-08-08 Zhengchu Guo , Lei Shi , Qiang Wu

Recent empirical work has shown that hierarchical convolutional kernels inspired by convolutional neural networks (CNNs) significantly improve the performance of kernel methods in image classification tasks. A widely accepted explanation…

Machine Learning · Statistics 2022-06-06 Theodor Misiakiewicz , Song Mei

Based on the variable Hilbert scale interpolation inequality bounds for the error of regularisation methods are derived under range inclusions. In this context, new formulae for the modulus of continuity of the inverse of bounded operators…

Numerical Analysis · Mathematics 2010-05-24 Markus Hegland , Bernd Hofmann

We study over-parameterized classifiers where Empirical Risk Minimization (ERM) for learning leads to zero training error. In these over-parameterized settings there are many global minima with zero training error, some of which generalize…

Machine Learning · Computer Science 2023-12-05 Julius Martinetz , Thomas Martinetz

Motivated by classical results of approximation theory, we define an Hermite-type interpolation in terms of $n$-dimensional subspaces of the space of $n$ times continuously differentiable functions. In the main result of this paper, we…

Classical Analysis and ODEs · Mathematics 2024-12-12 Ali Hasan Ali , Zsolt Páles

Overparameterized models may have many interpolating solutions; implicit regularization refers to the hidden preference of a particular optimization method towards a certain interpolating solution among the many. A by now established line…

Machine Learning · Computer Science 2024-09-18 Hung-Hsu Chou , Holger Rauhut , Rachel Ward

The rule of thumb regarding the relationship between the bias-variance tradeoff and model size plays a key role in classical machine learning, but is now well-known to break down in the overparameterized setting as per the double descent…

Machine Learning · Statistics 2026-02-16 Qingyi Hu , Liam Hodgkinson

There are many uses for linear fitting; the context here is interpolation and denoising of data, as when you have calibration data and you want to fit a smooth, flexible function to those data. Or you want to fit a flexible function to…

Data Analysis, Statistics and Probability · Physics 2021-09-22 David W. Hogg , Soledad Villar

We study the transfer learning process between two linear regression problems. An important and timely special case is when the regressors are overparameterized and perfectly interpolate their training data. We examine a parameter transfer…

Machine Learning · Computer Science 2022-09-29 Yehuda Dar , Richard G. Baraniuk

Discretization of the uniform norm of functions from a given finite dimensional subspace of continuous functions is studied. We pay special attention to the case of trigonometric polynomials with frequencies from an arbitrary finite set…

Numerical Analysis · Mathematics 2021-12-14 Boris Kashin , Sergei Konyagin , Vladimir Temlyakov

In this paper we propose a new framework for analyzing the performance of preprocessing algorithms. Our framework builds on the notion of kernelization from parameterized complexity. However, as opposed to the original notion of…

Data Structures and Algorithms · Computer Science 2016-11-07 Daniel Lokshtanov , Fahad Panolan , M. S. Ramanujan , Saket Saurabh

We study optimal procedures for estimating a linear functional based on observational data. In many problems of this kind, a widely used assumption is strict overlap, i.e., uniform boundedness of the importance ratio, which measures how…

Statistics Theory · Mathematics 2023-01-18 Wenlong Mou , Peng Ding , Martin J. Wainwright , Peter L. Bartlett

We present precise anisotropic interpolation error estimates for smooth functions using a new geometric parameter and derive inverse inequalities on anisotropic meshes. In our theory, the interpolation error is bounded in terms of the…

Numerical Analysis · Mathematics 2022-08-03 Hiroki Ishizaka , Kenta Kobayashi , Takuya Tsuchiya

We prove statistical rates of convergence for kernel-based least squares regression from i.i.d. data using a conjugate gradient algorithm, where regularization against overfitting is obtained by early stopping. This method is related to…

Statistics Theory · Mathematics 2016-07-11 Gilles Blanchard , Nicole Krämer