arXiv stat.ML
· Papers
From Global to Local: A Scalable Benchmark for Local Posterior Sampling
arXiv:2507.21449v2 Announce Type: replace Abstract: Degeneracy is an inherent feature of the loss landscape of neural networks, but it is not well understood how stochastic gradient MCMC (SGMCMC) algorithms interact with this degeneracy. In particular, existing global convergence guarantees for common SGMCMC algorithms