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.
Bridging the gap between constant step size stochastic gradient descent and Markov chains
4 Pith papers cite this work, alongside 81 external citations. Polarity classification is still indexing.
4
Pith papers citing it
81
external citations · OpenAlex
years
2026 4verdicts
UNVERDICTED 4representative citing papers
New discrete-time approximations to SG(L)D enable accurate non-asymptotic predictions of covariance and integrated autocorrelation time for practical tuning in large-batch or misspecified regimes.
Derives matrix concentration inequalities for time-inhomogeneous Markov chains under positive Ollivier-Ricci curvature or Saloff-Coste-Zuniga spectral gap, illustrated on dynamic Bradley-Terry-Luce models.
Constant stepsize SA with decision-dependent Markovian noise has stationary bias O(alpha) under Poisson-Gateaux differentiability, plus finite-time moment bounds and weak convergence.
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.
-
Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo
New discrete-time approximations to SG(L)D enable accurate non-asymptotic predictions of covariance and integrated autocorrelation time for practical tuning in large-batch or misspecified regimes.
-
Matrix concentration inequalities for time-inhomogeneous Markov chains
Derives matrix concentration inequalities for time-inhomogeneous Markov chains under positive Ollivier-Ricci curvature or Saloff-Coste-Zuniga spectral gap, illustrated on dynamic Bradley-Terry-Luce models.
-
Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
Constant stepsize SA with decision-dependent Markovian noise has stationary bias O(alpha) under Poisson-Gateaux differentiability, plus finite-time moment bounds and weak convergence.