English
Related papers

Related papers: A Note on Non-Negative $L_1$-Approximating Polynom…

200 papers

We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal…

Classical Analysis and ODEs · Mathematics 2021-01-05 Jonathan W. Siegel , Jinchao Xu

Motivated by numerical methods for solving parametric partial differential equations, this paper studies the approximation of multivariate analytic functions by algebraic polynomials. We introduce various anisotropic model classes based on…

Numerical Analysis · Mathematics 2020-01-17 Andrea Bonito , Ronald DeVore , Diane Guignard , Peter Jantsch , Guergana Petrova

Weighted least squares polynomial approximation uses random samples to determine projections of functions onto spaces of polynomials. It has been shown that, using an optimal distribution of sample locations, the number of samples required…

Numerical Analysis · Mathematics 2017-10-10 Abdul-Lateef Haji-Ali , Fabio Nobile , Raúl Tempone , Sören Wolfers

Let $g: \{-1,1\}^k \to \{-1,1\}$ be any Boolean function and $q_1,\dots,q_k$ be any degree-2 polynomials over $\{-1,1\}^n.$ We give a \emph{deterministic} algorithm which, given as input explicit descriptions of $g,q_1,\dots,q_k$ and an…

Computational Complexity · Computer Science 2013-11-28 Anindya De , Ilias Diakonikolas , Rocco A. Servedio

Numerical solutions of differential equations are usually not smooth functions. However, they should resemble the smoothness of the corresponding real solutions in one way or another. In two of our recent papers, a kind of spacial…

Numerical Analysis · Mathematics 2012-07-13 Tong Sun

We study the improper learning of multi-layer neural networks. Suppose that the neural network to be learned has $k$ hidden layers and that the $\ell_1$-norm of the incoming weights of any neuron is bounded by $L$. We present a kernel-based…

Machine Learning · Computer Science 2015-10-14 Yuchen Zhang , Jason D. Lee , Michael I. Jordan

We consider the optimal approximate posterior over the top-layer weights in a Bayesian neural network for regression, and show that it exhibits strong dependencies on the lower-layer weights. We adapt this result to develop a correlated…

Machine Learning · Statistics 2021-06-23 Sebastian W. Ober , Laurence Aitchison

Given $k\in N$, a nonnegative function $f\in C^r[a,b]$, $r\ge 0$, an arbitrary finite collection of points $\big\{\alpha_i\big\}_{i\in J} \subset [a,b]$, and a corresponding collection of nonnegative integers $\big\{m_i\big\}_{i\in J}$ with…

Classical Analysis and ODEs · Mathematics 2023-05-04 German Dzyubenko , Kirill A. Kopotun

Signal processing in non-Gaussian noise environment is addressed in this paper. For many real-life situations, the additive noise process present in the system is found to be dominantly non-Gaussian. The problem of detection and estimation…

Statistics Theory · Mathematics 2014-01-23 Jugalkishore K. Banoth , Pradip Sircar

In this paper we study constrained subspace approximation problem. Given a set of $n$ points $\{a_1,\ldots,a_n\}$ in $\mathbb{R}^d$, the goal of the {\em subspace approximation} problem is to find a $k$ dimensional subspace that best…

Data Structures and Algorithms · Computer Science 2025-04-30 Aditya Bhaskara , Sepideh Mahabadi , Madhusudhan Reddy Pittu , Ali Vakilian , David P. Woodruff

We give the first polynomial-time algorithm for the testable learning of halfspaces in the presence of adversarial label noise under the Gaussian distribution. In the recently introduced testable learning model, one is required to produce a…

Machine Learning · Computer Science 2023-03-10 Ilias Diakonikolas , Daniel M. Kane , Vasilis Kontonis , Sihan Liu , Nikos Zarifis

We show in this paper that a one-layer feedforward neural network with exponential activation functions in the inner layer and logarithmic activation in the output neuron is an universal approximator of convex functions. Such a network…

Neural and Evolutionary Computing · Computer Science 2020-03-09 Giuseppe C. Calafiore , Stephane Gaubert , Corrado Possieri

We study active learning (AL) based on Gaussian Processes (GPs) for efficiently enumerating all of the local minimum solutions of a black-box function. This problem is challenging due to the fact that local solutions are characterized by…

Machine Learning · Statistics 2019-03-11 Yu Inatsu , Daisuke Sugita , Kazuaki Toyoura , Ichiro Takeuchi

For various Hilbert spaces of analytic functions on the unit disk, we characterize when a function $f$ has optimal polynomial approximants given by truncations of a single power series. We also introduce a generalized notion of optimal…

Functional Analysis · Mathematics 2023-07-11 Christopher Felder

We study polyhedral approximations to the cone of nonnegative polynomials. We show that any constant ratio polyhedral approximation to the cone of nonnegative degree $2d$ forms in $n$ variables has to have exponentially many facets in terms…

Optimization and Control · Mathematics 2019-03-27 Alperen A. Ergür

We consider in this paper a class of single-ratio fractional minimization problems, in which the numerator part of the objective is the sum of a nonsmooth nonconvex function and a smooth nonconvex function while the denominator part is a…

Optimization and Control · Mathematics 2020-12-23 Na Zhang , Qia Li

While score-based generative models (SGMs) have achieved remarkable success in enormous image generation tasks, their mathematical foundations are still limited. In this paper, we analyze the approximation and generalization of SGMs in…

Machine Learning · Statistics 2024-02-26 Frank Cole , Yulong Lu

Approximations for an unknown density $g$ in terms of a reference density $f_\nu$ and its associated orthonormal polynomials are discussed. The main application is the approximation of the density $f$ of a sum $S$ of lognormals which may…

Probability · Mathematics 2016-01-11 Søren Asmussen , Pierre-Olivier Goffard , Patrick J. Laub

We study worst-case optimal approximation of positive linear functionals in reproducing kernel Hilbert spaces induced by increasingly flat Gaussian kernels. This provides a new perspective and some generalisations to the problem of…

Numerical Analysis · Mathematics 2020-01-10 Toni Karvonen , Simo Särkkä

Due to their flexibility, Gaussian processes (GPs) have been widely used in nonparametric function estimation. A prior information about the underlying function is often available. For instance, the physical system (computer model output)…

Methodology · Statistics 2017-11-21 Hassan Maatouk