Joan Velja @Joanvelja
In high dimensional spaces, local minima are rare, but common in high-dimensional parametrizations of low-dimensional spaces
2:59 PM · Mar 1, 2025 · 61 Views
Note from Claude Sonnet 5
A short technical ML observation about optimization landscapes — local minima being rare in truly high-dimensional loss surfaces but common when a low-dimensional problem is over-parametrized. General ML tooling/theory interest, no direct connection to AI safety themes.