Parallel Training of Deep Networks with Local Updates

1 code implementation • 7 Dec 2020 • Michael Laskin, Luke Metz, Seth Nabarro, Mark Saroufim, Badreddine Noune, Carlo Luschi, Jascha Sohl-Dickstein, Pieter Abbeel

Deep learning models trained on large data sets have been widely successful in both vision and language domains.

Aren't we all nearest neighbors: Spatial trees, high dimensional reductions and batch nearest neighbor search

1 code implementation • 13 Jul 2015 • Mark Saroufim

We start with a review of the pervasiveness of the nearest neighbor search problem and techniques used to solve it along with some experimental results.

Computational Geometry Data Structures and Algorithms