A scalable benchmark using deep linear networks shows RMSProp-preconditioned SGLD most accurately estimates the local learning coefficient, a degeneracy-aware measure of posterior geometry, up to 100M parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Global to Local: A Scalable Benchmark for Local Posterior Sampling
A scalable benchmark using deep linear networks shows RMSProp-preconditioned SGLD most accurately estimates the local learning coefficient, a degeneracy-aware measure of posterior geometry, up to 100M parameters.