pith. sign in

When din ≫d out and C2 0 C4 1 R2 is large, PAC-Bayes can still be favorable despite thedin term, because it avoids the spectral norm constants entirely

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

stat.ML 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Singular Bayesian Neural Networks

stat.ML · 2026-01-30 · unverdicted · novelty 7.0

Low-rank weight factorization creates singular posteriors in Bayesian neural networks that scale as sqrt(r(m+n)) in complexity and use up to 33x fewer parameters than ensembles.

citing papers explorer

Showing 1 of 1 citing paper.

  • Singular Bayesian Neural Networks stat.ML · 2026-01-30 · unverdicted · none · ref 13

    Low-rank weight factorization creates singular posteriors in Bayesian neural networks that scale as sqrt(r(m+n)) in complexity and use up to 33x fewer parameters than ensembles.