AI ALIGNMENT FORUM
AF

Wikitags

Singular Learning Theory

Edited by DanielFilan last updated 20th Jun 2023

Singluar learning theory is a theory that applies algebraic geometry to statistical learning theory, developed by Sumio Watanabe. Reference textbooks are "the grey book", Algebraic Geometry and Statistical Learning Theory, and "the green book", Mathematical Theory of Bayesian Statistics.

Subscribe
1
Subscribe
1
Discussion0
Discussion0
Posts tagged Singular Learning Theory
26DSLT 0. Distilling Singular Learning Theory
Liam Carroll
2y
0
19DSLT 1. The RLCT Measures the Effective Dimension of Neural Networks
Liam Carroll
2y
0
11DSLT 3. Neural Networks are Singular
Liam Carroll
2y
0
14DSLT 2. Why Neural Networks obey Occam's Razor
Liam Carroll
2y
0
67Neural networks generalize because of this one weird trick
Jesse Hoogland
3y
6
75Announcing Timaeus
Jesse Hoogland, Daniel Murfet, Alexander Gietelink Oldenziel, Stan van Wingerden
2y
4
80Timaeus's First Four Months
Jesse Hoogland, Daniel Murfet, Stan van Wingerden, Alexander Gietelink Oldenziel
2y
1
42Investigating the learning coefficient of modular addition: hackathon project
Nina Panickssery, Dmitry Vaintrob
2y
1
33Growth and Form in a Toy Model of Superposition
Liam Carroll, Edmund Lau
2y
0
20Spooky action at a distance in the loss landscape
Jesse Hoogland, Filip Sondej
3y
1
14Gradient surfing: the hidden role of regularization
Jesse Hoogland
3y
7
16DSLT 4. Phase Transitions in Neural Networks
Liam Carroll
2y
0
86Towards Developmental Interpretability
Jesse Hoogland, Alexander Gietelink Oldenziel, Daniel Murfet, Stan van Wingerden
2y
2
50Simple versus Short: Higher-order degeneracy and error-correction
Daniel Murfet
1y
1
39Stagewise Development in Neural Networks
Jesse Hoogland, Liam Carroll, Daniel Murfet
1y
1
Load More (15/28)
Add Posts