Explicit scaling prescriptions for hyperparameters in DenseAMs are derived from model dynamics and shown to match empirical results across scales.
Deep linear network training dynamics from random initialization: Data, width, depth, and hyperparameter transfer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hyperparameter Transfer for Dense Associative Memories
Explicit scaling prescriptions for hyperparameters in DenseAMs are derived from model dynamics and shown to match empirical results across scales.