29 citations · 60 across the 28 of their papers we have counts for
3 papers · 1 filter
Deep Learning with Nonsmooth Objectives
Vinesha Peiris, Nadezda Sukhorukova, Vera Roshchina
We explore the potential for using a nonsmooth loss function based on the max-norm in the training of an artificial neural network. We hypothesise that this may lead to superior cl…
The intrinsic core and minimal faces of convex sets in general vector spaces
R. Díaz Millán, Vera Roshchina
Intrinsic core generalises the finite-dimensional notion of the relative interior to arbitrary (real) vector spaces. Our main goal is to provide a self-contained overview of the ke…
Hyperbolicity cones are amenable
Bruno F. Lourenço, Vera Roshchina, James Saunderson
Amenability is a notion of facial exposedness for convex cones that is stronger than being facially dual complete (or "nice") which is, in turn, stronger than merely being facially…