Hacker News new | ask | show | jobs
by alexcnwy 3154 days ago
I think you're misinterpreting the parent who is saying that local minima are not a problem in high dimensions because there is always a dimension to move in that reduces the loss (unlike in lower dimensions where you can get stuck in a point across all dimensions that cannot be locally improved upon)
1 comments

I still don't understand what the parent is talking about then. Could you please restate the explanation using math notation/terminology?