Re:An Idiot’s guide to Support vector machines (2003) [pdf]
by currymj on Tuesday January 01, 2019 @01:28AM
(#18799242)
As others have said, you don't actually want the global optimum of a neural network because that would be terrible overfitting. There is some evidence that architectural tricks (like ResNet) that empirically help performance are making the loss landscape "more convex", though.
https://arxiv.org/pdf/1712.09913.pdf