Robust and resource efficient identification of shallow neural networks by fewest samples
From MaRDI portal
Publication:5155957
DOI10.1093/imaiai/iaaa036OpenAlexW3124274991MaRDI QIDQ5155957
Ingrid Daubechies, Jan Vybíral, Massimo Fornasier
Publication date: 13 October 2021
Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1804.01592
whiteningrandomized algorithmsbreaking the curse of dimensionalitynonlinear programming for optimizations in matrix subspacestraining shallow neural networks
Artificial neural networks and deep learning (68T07) Nonlinear programming (90C30) Randomized algorithms (68W20)
Related Items (4)
Efficient Identification of Butterfly Sparse Matrix Factorizations ⋮ Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples ⋮ Information theory and recovery algorithms for data fusion in Earth observation ⋮ Robust and resource-efficient identification of two hidden layer neural networks
This page was built for publication: Robust and resource efficient identification of shallow neural networks by fewest samples
