On the saddle point problem for non-convex optimization — mentioned by shmel

Fri, 04 Dec 2015 18:20:25 GMT

Mainly because in high-dimensional space saddle points are much more common and many local minima have very close fitness. Look for example http://arxiv.org/abs/1405.4604 and following papers.

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

On the saddle point problem for non-convex optimization · HackerPapers discussions

On the saddle point problem for non-convex optimization — mentioned by shmel