wassname/ml-debug
1
0
Fork 0
mirror of https://github.com/wassname/ml-debug.git synced 2026-06-27 17:49:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update loss_surface.md

Browse Source
This commit is contained in:
wassname (Michael J Clark)
2026-06-11 21:21:01 +08:00
committed by GitHub
parent 6e9a3ca633
commit 1ad74e14c6
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
refs/loss_surface.md
+2
View File
@@ -68,3 +68,5 @@ When your loss is a product of factors A*B and one factor can be near zero:
``` ```
General principle: if you want gradient to flow independently through two factors, decompose multiplicatively in log space. General principle: if you want gradient to flow independently through two factors, decompose multiplicatively in log space.
You can also design surrogate losses that are better behaved but move in the right direction in a better behaved well.