559 citations · 1.5k across the 55 of their papers we have counts for
3 papers · 1 filter
Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers
Bubacarr Bah, Holger Rauhut, Ulrich Terstiege +1
We study the convergence of gradient flows related to learning deep linear neural networks (where the activation function is the identity map) from data. In this case, the composit…
On the geometry of polytopes generated by heavy-tailed random vectors
Olivier Guédon, Felix Krahmer, Christian Kümmerle +2
We study the geometry of centrally-symmetric random polytopes, generated by independent copies of a random vector taking values in . We show that under minima…
Jointly Low-Rank and Bisparse Recovery: Questions and Partial Answers
Simon Foucart, Rémi Gribonval, Laurent Jacques +1
We investigate the problem of recovering jointly -rank and -bisparse matrices from as few linear measurements as possible, considering arbitrary measurements as well as rank-…