3 papers
cs.CL2026
Can small transformers learn the language of Coxeter groups?
J. Elisenda Grigsby, Yiyao Huang, Arushi Katyal +3
The field of mechanistic interpretability is well-suited to collaborative projects between mathematicians and AI researchers. This work describes one such project. We trained a sma…
cs.LG2026
A Complete Symmetry Classification of Shallow ReLU Networks
Pranavkrishnan Ramakrishnan
Parameter space is not function space for neural network architectures. This fact, investigated as early as the 1990s under terms such as ``reverse engineering," or ``parameter ide…
math.AG2023
The Arithmetic of Elliptic Pairs and An -variable Artin Conjecture
Pranavkrishnan Ramakrishnan
The theory of elliptic pairs, as investigated in a paper by Castravet, Laface, Tevelev, and Ugaglia, provides useful conditions to determine polyhedrality of the pseudo-effective c…