From 1ad74e14c62cc96b183cf1cf05f20f29a5c85a10 Mon Sep 17 00:00:00 2001
From: "wassname (Michael J Clark)" <1103714+wassname@users.noreply.github.com>
Date: Thu, 11 Jun 2026 21:21:01 +0800
Subject: [PATCH] Update loss_surface.md

---
 refs/loss_surface.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/refs/loss_surface.md b/refs/loss_surface.md
index 5537b21..9af03e2 100644
--- a/refs/loss_surface.md
+++ b/refs/loss_surface.md
@@ -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.
+
+You can also design surrogate losses that are better behaved but move in the right direction in a better behaved well.