GCR

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Jun 29 19:52
Editor
Edited
Edited
2025 Jun 29 20:14

Group Composition via Representations

This paper analyzes how the GCR (Group Composition via Representations) algorithm based on
Representation Theory
is implemented in small neural networks trained on
Finite Group
addition and multiplication through reverse engineering.

Method

The architecture was divided into four weight blocks from the beginning - "left embedding / right embedding / MLP / unembedding" - but this structure (embedding×2 + MLP + unembedding) was trained entirely end-to-end and then the learned weights were reverse-engineered to identify and interpret "these four blocks each store, compute, and retrieve representation matrices." These weights function as lookup tables that store and retrieve "Representation matrix" values. The trained weight sets store the representation matrices of specific finite groups directly as embedding tables, allowing the network to perform predefined algorithms.

Results

Dihedral Group
data is represented by 2-dimensional standard representation (rotation+reflection), while
Symmetric Group
shows 1-dimensional sign representation and n-1 dimensional standard representation.
Permutation Group
exhibits 1-dimensional trivial representation, 1-dimensional sign representation, n-1 dimensional standard representation, and standard ⊗ sign
Kronecker product
dimensions, along with higher-dimensional representations corresponding to
Young tableau
when needed.
notion image

Insights

Learning progresses in three stages: memorization → circuit formation → cleanup, and shows that generalization performance improves dramatically only after universal circuits are formed. While all models use variants of the GCR algorithm, they differ randomly in which irreducible representations they learn, how many, and in what order, refuting "strong universality" but supporting "weak universality" (existence of general principles).
 
 
 
 

A Toy Model of Universality (2023)

 
 
 

Recommendations