8 citations · 8 across the 4 of their papers we have counts for
Showing stat.COShow all
2 papers · 1 filter
stat.CO2026
SULA: Robust Langevin Sampling via Drift-Diffusion Saturation
Ritik Soni, Dootika Vats
The unadjusted Langevin algorithm (ULA) and its stochastic-gradient variant, SGLD, are workhorses of modern Bayesian machine learning, but can be fragile when faced with a target d…
stat.CO2026
Optimal Scaling of Langevin Proposals with Generalized Acceptance Rules
Ritik Soni, Dootika Vats
Langevin-based Markov chain Monte Carlo (MCMC) algorithms use gradient information to improve sampling, particularly in high dimensions. Classical optimal scaling theory for these…