no code implementations • 13 Jul 2022 • Mario Lezcano-Casado
We present the classical coordinate-free formalism for forward and backward mode ad in the real and complex setting.
no code implementations • 9 Mar 2022 • Mario Lezcano-Casado
We design and implement a Python library to help the non-expert using all these powerful tools in a way that is efficient, extensible, and simple to incorporate into the workflow of the data scientist, practitioner, and applied researcher.
no code implementations • 9 Oct 2020 • Mario Lezcano-Casado
We introduce a framework to generalize adaptive and momentum methods to arbitrary manifolds by noting that for every differentiable manifold, there exists a radially convex open set that covers almost all the manifold.
no code implementations • 6 Aug 2020 • Mario Lezcano-Casado
We give curvature-dependant convergence rates for the optimization of weakly convex functions defined on a manifold of 1-bounded geometry via Riemannian gradient descent and via the dynamic trivialization algorithm.
2 code implementations • 20 Sep 2019 • Mario Lezcano-Casado
We prove conditions under which a trivialization is sound in the context of gradient-based optimization and we show how two large families of trivializations have overall favorable properties, but also suffer from a performance issue.
3 code implementations • 24 Jan 2019 • Mario Lezcano-Casado, David Martínez-Rubio
We demonstrate how our method constitutes a more robust approach to optimization with orthogonal constraints, showing faster, accurate, and more stable convergence in several tasks designed to test RNNs.