2026
Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation
ICML 2026poster
Stochastic-gradient MCMC methods enable scalable Bayesian posterior sampling but often suffer from sensitivity to minibatch size and gradient noise. To address this, we propose Stochastic Gradient Lattice Random Walk (SGLRW), an extension of the Lattice Random Walk discretization. Unlike conventiona…