Hi,
Do you recommend any papers that talks more about why we have changed about the way we currently think about Local Optima in a Higher Dimensional Spaces?
Yes! There is a great paper from Yann Lecun’s group that specifically addresses those issues. Here is a thread that includes a link to that: https://community.deeplearning.ai/t/cost-function-stuck-at-local-minima/95214/4?u=paulinpaloalto