implicit regularization: Nonlinear Function
Created: February 23, 2021
Modified: March 02, 2022

implicit regularization

This page is from my personal notes, and has not been specifically reviewed for public consumption. It might be incomplete, wrong, outdated, or stupid. Caveat lector.

Examples:

Links to this note

deceptive alignment

The idea is that a [ mesa optimizer|mesa-optimizing ] policy with access to sufficient information about the world (e.g., web search) might…

double descent

Empirically, as model capacity increases past the memorization threshold ( ), [ generalization|generalization ] error starts decreasing…

Meta
Tagged With: