HackerPapers

arXiv:1602.04915stat.ML

Gradient Descent Converges to Minimizers

Jason D. Lee, Max Simchowitz, Michael I. Jordan, Benjamin Recht

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

We show that gradient descent converges to a local minimizer, almost surely with random initialization. This is proved by applying the Stable Manifold Theorem from dynamical systems theory.

arXiv comments
Submitted to COLT 2016
Journal reference
DOI
Subjects
stat.MLMachine Learning (Statistics) cs.LGMachine Learning math.OCOptimization and Control

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jun 2020 to Jun 2020.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. Implement your own source transformation AD with Julia 1 comment

    • Depending on the level you're looking for, I'm always a huge fan of Rockafellar [0] for the more mathematical expositions (they're lovely, clear, and very well thought through). Even in this case, though, subgradients may not exist (they're only guaranteed to exist for convex…

      LolWolfView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.