Timo Klock

A. Elmokashfi, S. W. Funke, T. Klock, M. Kuchta, V. Naumova and J. J. Uv

Digital tracing, validation, and reporting

Smittestopp − A Case Study on Digital Contact Tracing

T. Klock

A deep network construction that adapts to intrinsic dimensionality beyond the domain

Neural Networks

M. Fornasier, T. Klock and K. Riedl

Consensus-based optimization methods converge globally in mean-field law

arXiv 2103.15130

Z. Kereta and T. Klock

Estimating covariance and precision matrices along subspaces

Electronic Journal of Statistics

T. Klock, S. Vigogna and A. Lanteri

Estimating multi-index models with response-conditional least squares

Electronic Journal of Statistics

C. Fiedler, M. Fornasier, T. Klock and M. Rauchensteiner

Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples

arXiv

J. Kileel, T. Klock and J. Pereira

Landscape analysis of an improved power method for tensor decomposition

Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)

T. Klock

Deep neural networks adapt to intrinsic dimensionality beyond the data domain

Applied Mathematics Seminar, KU Eichstätt, Germany

T. Klock

Model-based function learning in high dimensions

The University of Oslo

T. Klock and A. Cloninger

Adaptivity of Relu Nets Beyond Low-Dimensional Domains

Z. Kereta, T. Klock and V. Naumova

Nonlinear generalization of the monotone single index model

Information and Inference

M. Fornasier, T. Klock and M. Rauchensteiner

Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks

Constructive Approximation

M. Fornasier, T. Klock and M. Rauchensteiner

Identifying weights of overcomplete shallow- and two layer neural networksusing few network evaluations

Z. Kereta, T. Klock and V. Naumova

Covariance and precision matrix estimation, and dimension reduction in regression problems

Oslo, Norway

Z. Kereta, T. Klock and V. Naumova

Towards nonlinear sufficient dimension reduction

AIP conference, Grenoble, France

M. Grasmair, T. Klock and V. Naumova

Adaptive multi-penalty regularization based on a generalized Lasso path

Applied and Computational Harmonic Analysis

Z. Kereta, T. Klock and V. Naumova

A geometrical approach for nonlinear single-index model estimation

Z. Kereta, T. Klock and V. Naumova

High-dimensional function learning on curves

Z. Kereta, T. Klock and V. Naumova

Inference and estimation for nonlinear single index models

T. Klock

Adaptively estimating nonlinear single index models with monotonic link functions

Munich

V. Naumova and T. Klock

Multi-parameter regularization for solving inverse problems of unmixing type

University of Cambridge, UK

Z. Kereta, T. Klock and V. Naumova

Nonlinear estimation of single index models

Nonlinear Data: Theory and Algorithms Oberwolfach

M. Grasmair, T. Klock and V. Naumova

Adaptive multi-penalty regularization based on a generalized Lasso path

arXiv

T. Klock

Exact support recovery in unmixing problems by an altered Lasso-path algorithm for multi-penalty functionals

V. Naumova

Multi-parameter regularisation for solving unmixing problems in signal processing: theoretical and practical aspects

Mathematical Signal Processing and Data Analysis, Bremen, Germany

T. Klock

Support Recovery in Unmixing Problems using Multi-Penalty Regularization

Hangzhou, China