Diagonal EP under variance-profile Gaussian matrices produces Gaussian-process dynamics with profile-dependent memory instead of conventional scalar state evolution.
State evolution for general approximate message passing algorithms, with applications to spatial coupling,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
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.
For a spiked Wigner model with power-law inhomogeneous noise variances, the BBP transition is non-monotonic and inhomogeneous noise can enhance signal detectability.
citing papers explorer
-
Gaussian-Process Dynamics of Diagonal Expectation Propagation under Variance-Profile Gaussian Measurements
Diagonal EP under variance-profile Gaussian matrices produces Gaussian-process dynamics with profile-dependent memory instead of conventional scalar state evolution.
-
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.
-
BBP transition and the leading eigenvector of the spiked Wigner model with inhomogeneous noise
For a spiked Wigner model with power-law inhomogeneous noise variances, the BBP transition is non-monotonic and inhomogeneous noise can enhance signal detectability.