Exact finite-sample analysis reveals that the PPC-based selector for the learning rate η is η-invariant with known variance and flat prior, and data-independent with unknown variance and reference prior, collapsing to the smallest grid value before any data are observed.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When can a posterior predictive check identify the learning rate? Exact degeneracy in Gaussian models and implications for Generalised Bayesian Inerence
Exact finite-sample analysis reveals that the PPC-based selector for the learning rate η is η-invariant with known variance and flat prior, and data-independent with unknown variance and reference prior, collapsing to the smallest grid value before any data are observed.