Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models
Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect model selection in settings such as deep learning. The Widely Applicable Bayesian Information Criterion (WBIC) relies on local learning coefficients $λ$, which in the analytic case coincides with local Real Log Canonical Thresholds (RLCT) of the Kullback-Leibler divergence of the model, to capture correct marginal likelihood asymptotics. Exact computation of the learning coefficients has been limited to special cases, and only
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Exact Algebraic Computation of Learning Coefficients for Two” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Grégoire Sergeant-Perthuis →
“Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models”
- LinkedLinked via arxiv author · 85%Elias Tsigaridas →
“Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models”
- LinkedLinked via arxiv author · 85%Jules Tsukahara →
“Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models”