Gradient Descent Provably Optimizes Over-parameterized Neural Networks — mentioned by leecarraher

Tue, 12 Oct 2021 13:46:38 GMT

They also have an embedded link to this paper(https://arxiv.org/abs/1810.02054 ) regarding the provable convergence of neural networks by non-convex gradient descent optimization. You are correct, the researchers do no propose an alternative to sgd based training (or at least according to the article). It did seem like it was going toward an alternative training method, perhaps SMO on kernel SVM, but then it pivots to describing the theoretical result for infinte kernel svm from the linked article.

Paper and discussion history. A mention is not an endorsement.

Gradient Descent Provably Optimizes Over-parameterized Neural Networks — HN submission

Fri, 05 Oct 2018 20:15:42 GMT

Gradient Descent Provably Optimizes Over-Parameterized Neural Networks

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Gradient Descent Provably Optimizes Over-parameterized Neural Networks · HackerPapers discussions

Gradient Descent Provably Optimizes Over-parameterized Neural Networks — mentioned by leecarraher

Gradient Descent Provably Optimizes Over-parameterized Neural Networks — HN submission