Discussion about this post

User's avatar
rif a saurous's avatar

I think your err_ext decomposition has some sign errors?

Expand full comment
Joe Jordan's avatar

"It works in practice but not in theory."

But seriously though, I think the intuition from coin flips is misleading because 1d space still has a reasonable Euclidean metric but in the real world use cases (or anything above 9d) you don't want Euclidean but Manhattan metric. It gets even harder (for me at least) to have intuition about how nonlinearities impact a space and the metrics defining how far apart thing are. Basically I think it works because with enough parameters you can make points sufficiently, though probably not arbitrarily, far apart.

Expand full comment
4 more comments...

No posts