D-INL reduces training exchange by 70.4% while keeping accuracy within standard deviation of dense INL, with finite-rate regularization cutting estimated latent rate by 45.7% in a distributed classification experiment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sparse In-Network Learning via Shortest-Path Backpropagation and Finite-Rate Gating
D-INL reduces training exchange by 70.4% while keeping accuracy within standard deviation of dense INL, with finite-rate regularization cutting estimated latent rate by 45.7% in a distributed classification experiment.