Derives joint asymptotic jump-diffusion limit for global parameters and latent variables in SGLD-Gibbs under space-time rescaling, yielding explicit hyperparameter tuning guidance for calibrated uncertainty quantification.
Dynamical mean-field theory for stochastic gradient descent in G aussian mixture classification*
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative 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.
citing papers explorer
-
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
Derives joint asymptotic jump-diffusion limit for global parameters and latent variables in SGLD-Gibbs under space-time rescaling, yielding explicit hyperparameter tuning guidance for calibrated uncertainty quantification.
-
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.