S. Bamberger

activity

20172023

collaborators

4 papers

cs.LG2023

Approximating Positive Homogeneous Functions with Scale Invariant Neural Networks

Stefan Bamberger, Reinhard Heckel, Felix Krahmer

We investigate to what extent it is possible to solve linear inverse problems with $R e Lu$ networks. Due to the scaling invariance arising from the linearity, an optimal reconstruct…

cs.DS2021

Johnson-Lindenstrauss Embeddings with Kronecker Structure

Stefan Bamberger, Felix Krahmer, Rachel Ward

We prove the Johnson-Lindenstrauss property for matrices $Φ D_{ξ}$ where $Φ$ has the restricted isometry property and $D_{ξ}$ is a diagonal matrix containing the entries of a Kronecker…

math.PR2021

The Hanson-Wright Inequality for Random Tensors

Stefan Bamberger, Felix Krahmer, Rachel Ward

We provide moment bounds for expressions of the type $(X^{(1)} \otimes \dots \otimes X^{(d)})^{T} A (X^{(1)} \otimes \dots \otimes X^{(d)})$ where $\otimes$ denotes the Kronecker pro…

cs.DS2017

Optimal Fast Johnson-Lindenstrauss Embeddings for Large Data Sets

Stefan Bamberger, Felix Krahmer

Johnson-Lindenstrauss embeddings are widely used to reduce the dimension and thus the processing time of data. To reduce the total complexity, also fast algorithms for applying the…