Compute-optimally trained networks of different sizes show loss curves that collapse onto one universal curve after normalization; with learning rate decay, the collapse is tighter than seed-to-seed noise, providing a scaling-quality diagnostic.
Finite size scaling analysis of ising model block distribution functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
Compute-optimally trained networks of different sizes show loss curves that collapse onto one universal curve after normalization; with learning rate decay, the collapse is tighter than seed-to-seed noise, providing a scaling-quality diagnostic.