Replicating models and routing their local losses via permutations from a mixing kernel Q enables structured message sharing that improves generalization.
Entropic gradient descent algorithms and wide flat minima.Jour- nal of Statistical Mechanics: Theory and Experiment, 2021(12):124015
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
-
Improving Generalization by Permutation Routing Across Model Copies
Replicating models and routing their local losses via permutations from a mixing kernel Q enables structured message sharing that improves generalization.