T
Tristan Milne
Researcher at University of Toronto
Publications - 6
Citations - 25
Tristan Milne is an academic researcher from University of Toronto. The author has contributed to research in topics: Convex function & Piecewise. The author has an hindex of 3, co-authored 6 publications receiving 16 citations.
Papers
More filters
Posted Content
Piecewise Strong Convexity of Neural Networks.
TL;DR: The loss surface of a feed-forward neural network with ReLU non-linearities, regularized with weight decay, is studied to prove that local minima of the regularized loss function in this set are isolated, and that every differentiable critical point inThis set is a local minimum.
Journal ArticleDOI
Codomain rigidity of the Dirichlet to Neumann operator for the Riemannian wave equation
TL;DR: In this article, the Dirichlet to Neumann operator for the Riemannian wave equation on a compact manifold was studied and the authors proved that the DirICHlet to NN operator can be reconstructed from a compact RiemANNian manifold where sources and observations are on disjoint sets, provided a spectral condition on the Laplace-Beltrami operator is satisfied.
Proceedings Article
Piecewise Strong Convexity of Neural Networks
TL;DR: This article showed that the loss surface of a feed-forward neural network with ReLU nonlinearities, regularized with weight decay, is piecewise strongly convex on an important open set which contains, under some conditions, all of its global minimizers.
Posted Content
Wasserstein GANs with Gradient Penalty Compute Congested Transport
Tristan Milne,Adrian I. Nachman +1 more
TL;DR: In this article, it was shown that the gradient of Wasserstein GANs with Gradient Penalty (WGAN-GP) can compute the minimum of a different optimal transport problem, the so-called congested transport.