87 citations · 137 across the 23 of their papers we have counts for
29 papers
Multilayer Lookahead: a Nested Version of Lookahead
Denys Pushkin, Luis Barba
In recent years, SGD and its variants have become the standard tool to train Deep Neural Networks. In this paper, we focus on the recently proposed variant Lookahead, which improve…
Implicit Gradient Alignment in Distributed and Federated Learning
Yatin Dandi, Luis Barba, Martin Jaggi
A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and sto…
Dynamic Model Pruning with Feedback
Tao Lin, Sebastian U. Stich, Luis Barba +2
Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased…
Sharing a pizza: bisecting masses with two cuts
Luis Barba, Alexander Pilz, Patrick Schnider
Assume you have a pizza consisting of four ingredients (e.g., bread, tomatoes, cheese and olives) that you want to share with your friend. You want to do this fairly, meaning that…
Geodesic farthest-point Voronoi diagram in linear time
Luis Barba
Let be a simple polygon with vertices. For any two points in , the geodesic distance between them is the length of the shortest path that connects them among all paths c…
Asymmetric Convex Intersection Testing
Luis Barba, Wolfgang Mulzer
We consider asymmetric convex intersection testing (ACIT). Let be a set of points and a set of halfspaces in dimensions. We denot…