Limits RegistryPUBLIC RECORDLimits RegistryResearch Console →Posterior expected risk is controlled by empirical risk and divergence from a data-independent prior.
The question, scope, and sources behind this Registry record.
Under the recorded learning theory model, establish KL(Lhat(Q)||L(Q)) <= (KL(Q||P)+ln(2 sqrt(m)/delta))/m.
Current frontiers derived from accepted Claims.
Assertions tied to evidence, attribution, and review.
The frontier as it changed over time.
Only accepted Claims matching the current specification contribute to the displayed bounds. Strict inequalities remain open; contradictory Claims require editorial review.
No accepted machine-checked reproductions are recorded for this Limit.
Limits Registry. LR-003611. PAC-Bayes generalization bound. 2026.