Closed LinkToPast1990 closed 3 years ago
In principle, I think any reasonable methods would do the job (e.g., checking how the norm grows, etc). The code snippet you show tracks the growth of norm of the first element, which is just a faster, more-convenient, but likely accurate proxy.
Hi, @HanGuo97 Do we check the convergence of estimating the hvp by empirically tracking the estimate_norm_diff? Thanks!