Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
RELTA-SGLD: Relative-Growth Localized Taming for Nonconvex Stochastic-Gradient Langevin Learning
Yiwei Zhou, Ziheng Chen
We introduce RELTA-SGLD, a taming scheme that stabilizes superlinear stochastic-gradient updates while reducing unnecessary suppression of the original learning drift. A threshold…
stat.ML2026
Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling
Yiwei Zhou
Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own trajectory. We show that small f…