Massimo Fornasier

M. Fornasier, T. Klock and K. Riedl

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

arXiv 2103.15130

M. Fornasier, J. Maly and V. Naumova

Robust recovery of low-rank matrices with non-orthogonal sparse decomposition from incomplete measurements

Applied Mathematics and Computation

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

E. De Vito, M. Fornasier and V. Naumova

A machine learning approach to optimal Tikhonov regularization I: Affine manifolds

Analysis and Applications

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

M. Fornasier, E. De Vito, Z. Kereta and V. Naumova

Automated parameter estimation for selected inverse problems

Grenoble, France

M. Fornasier, J. Maly and V. Naumova

Robust Recovery of Low-Rank Matrices using Multi-Penalty Regularization

NIPS Workshop Optimisation for Machine Learning

V. Naumova, M. Fornasier and S. Pereverzyev

Parameter Choice Strategies for Multi-Penalty Regularization

SIAM Journal on Numerical Analysis

M. Fornasier, V. Naumova and S. Pereverzyev

Multi-Parameter Regularization and High-Dimensional Learning