Decoupled descent enforces asymptotic tracking of test error by training error in Gaussian mixture models through bias cancellation via approximate message passing, enabling full data utilization.
State evolution for approximate message passing with non-separable functions.Information and Inference: A Journal of the IMA, 9(1):33–79, January 2019
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
Decoupled descent enforces asymptotic tracking of test error by training error in Gaussian mixture models through bias cancellation via approximate message passing, enabling full data utilization.