For exponential family data, optimal FC-DNN parameters equal the RG fixed points of the input characteristic parameters, making training equivalent to RG coarse-graining.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Interpreting FCDNNs via RG on Exponential Family
For exponential family data, optimal FC-DNN parameters equal the RG fixed points of the input characteristic parameters, making training equivalent to RG coarse-graining.