Gradient-based dimension reduction of multivariate vector-valued functions

O Zahm, PG Constantine, C Prieur, YM Marzouk - SIAM Journal on Scientific …, 2020 - SIAM
Multivariate functions encountered in high-dimensional uncertainty quantification problems
often vary most strongly along a few dominant directions in the input parameter space. We …

[BOOK][B] Ridge functions

A Pinkus - 2015 - books.google.com
Ridge functions are a rich class of simple multivariate functions which have found
applications in a variety of areas. These include partial differential equations (where they are …

[BOOK][B] Ridge functions and applications in neural networks

VE Ismailov - 2021 - books.google.com
Recent years have witnessed a growth of interest in the special functions called ridge
functions. These functions appear in various fields and under various guises. They appear in …

Tractability of sampling recovery on unweighted function classes

D Krieg - Proceedings of the American Mathematical Society …, 2024 - ams.org
It is well-known that the problem of sampling recovery in the $ L_2 $-norm on unweighted
Korobov spaces (Sobolev spaces with mixed smoothness) as well as classical smoothness …

Counting via entropy: new preasymptotics for the approximation numbers of Sobolev embeddings

T Kühn, S Mayer, T Ullrich - SIAM Journal on Numerical Analysis, 2016 - SIAM
In this paper, we reveal a new connection between approximation numbers of periodic
Sobolev type spaces, where the smoothness weights on the Fourier coefficients are induced …

Robust and resource-efficient identification of two hidden layer neural networks

M Fornasier, T Klock, M Rauchensteiner - Constructive Approximation, 2019 - Springer
We address the structure identification and the uniform approximation of two fully nonlinear
layer neural networks of the type f (x)= 1^ T h (B^ T g (A^ T x)) f (x)= 1 T h (BT g (AT x)) …

[HTML][HTML] Gelfand numbers related to structured sparsity and Besov space embeddings with small mixed smoothness

S Dirksen, T Ullrich - Journal of Complexity, 2018 - Elsevier
We consider the problem of determining the asymptotic order of the Gelfand numbers of
mixed-(quasi-) norm embeddings ℓ pb (ℓ qd)↪ ℓ rb (ℓ ud) given that p≤ r and q≤ u, with …

Robust and resource efficient identification of shallow neural networks by fewest samples

M Fornasier, J Vybíral… - Information and Inference …, 2021 - academic.oup.com
We address the structure identification and the uniform approximation of sums of ridge
functions on, representing a general form of a shallow feed-forward neural network, from a …

Stable recovery of entangled weights: Towards robust identification of deep neural networks from minimal samples

C Fiedler, M Fornasier, T Klock… - Applied and …, 2023 - Elsevier
In this paper we approach the problem of unique and stable identifiability from a finite
number of input-output samples of generic feedforward deep artificial neural networks of …

Tractability of the approximation of high-dimensional rank one tensors

E Novak, D Rudolf - Constructive Approximation, 2016 - Springer
We study the approximation of high-dimensional rank one tensors using point evaluations
and consider deterministic as well as randomized algorithms. We prove that for certain …