4 papers
Energy Propagation in Scattering Convolution Networks Can Be Arbitrarily Slow
Hartmut Führ, Max Getter
We analyze energy decay for deep convolutional neural networks employed as feature extractors, including Mallat's wavelet scattering transform. For time-frequency scattering transf…
The Restricted Isometry Property for Measurements from Group Orbits
Hartmut Führ, Timm Gilles
It is known that sparse recovery by measurements from random circulant matrices provides good recovery bounds. We generalize this to measurements that arise as a random orbit of a…
Sparse Recovery from Group Orbits
Timm Gilles, Hartmut Führ
While most existing sparse recovery results allow only minimal structure within the measurement scheme, many practical problems possess significant structure. To address this gap,…
Consistent sampling of Paley-Wiener functions on graphons
Hartmut Führ, Mahya Ghandehari
We study sampling methods for Paley-Wiener functions on graphons, thereby adapting and generalizing methods initially developed for graphs to the graphon setting. We then derive co…