Mechanism of recursion-driven generalization gains
Explain why deep recursion with supervision yields superior generalization compared to larger and deeper non-recursive networks, and develop a theoretical account beyond overfitting speculation.
References
Although we simplified and improved on deep recursion, the question of why recursion helps so much compared to using a larger and deeper network remains to be explained; we suspect it has to do with overfitting, but we have no theory to back this explaination.
— Less is More: Recursive Reasoning with Tiny Networks
(Jolicoeur-Martineau, 6 Oct 2025) in Conclusion