2 citations · 2 across the 2 of their papers we have counts for
6 papers
Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples
Christian Fiedler, Massimo Fornasier, Timo Klock +1
In this paper we approach the problem of unique and stable identifiability of generic deep artificial neural networks with pyramidal shape and smooth activation functions from a fi…
A deep network construction that adapts to intrinsic dimensionality beyond the domain
Alexander Cloninger, Timo Klock
We study the approximation of two-layer compositions via deep networks with ReLU activation, where is a geometrically intuitive, dimensionality reducing featur…
Estimating multi-index models with response-conditional least squares
Timo Klock, Alessandro Lanteri, Stefano Vigogna
The multi-index model is a simple yet powerful high-dimensional regression model which circumvents the curse of dimensionality assuming for s…
Estimating covariance and precision matrices along subspaces
Zeljko Kereta, Timo Klock
We study the accuracy of estimating the covariance and the precision matrix of a -variate sub-Gaussian distribution along a prescribed subspace or direction using the finite sam…
Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks
Massimo Fornasier, Timo Klock, Michael Rauchensteiner
We address the structure identification and the uniform approximation of two fully nonlinear layer neural networks of the type on from a sm…
Nonlinear generalization of the monotone single index model
Zeljko Kereta, Timo Klock, Valeriya Naumova
Single index model is a powerful yet simple model, widely used in statistics, machine learning, and other scientific fields. It models the regression function as , where…