[Re] VAE Approximation Error: ELBO and Exponential Families

On a tractable latent-variable model, how large is the gap between the computed ELBO and an independently evaluated log likelihood?

Use numerical integration or enumeration controlled by the evaluator and report integration error separately from variational approximation error.

What you could produce

• Versioned protocol, input and environment manifest, and independent per-case comparison table including uncertainty and incomplete cases.

Before you use it

• PyTorch (named in journal metadata; dependency version not checked)

Limits to keep in view

• No research code was executed; no independent scientific verification has been performed.
• The current qualified pilot is self-contained Python 3.13 with a 90-second author deadline. This article's environment has not been qualified for that path.
• Published source metadata and a historical review do not establish compatibility, successful reproduction, operator independence or current scientific correctness.
• Dependencies named in metadata are not available under the current standard-library-only pilot; a new qualified environment is required.

Source and permission context

Kyrylov, Volodymyr; Bedi, Navdeep Singh; Zang, Qianbo. [Re] VAE Approximation Error: ELBO and Exponential Families. ReScience C 9(2), #37; 10.5281/zenodo.8173745.

Catalog listing reviewed. This review covers the description and source links displayed here.

ReScience/Zenodo metadata reviewed; exact CC-BY-4.0 evidence is manuscript-scoped.

Reviewed 2026-09-14. Copying or adapting source files remains subject to their own terms.

Before copying source material

• The associated code's exact license and version-specific third-party notices have not been independently checked.
• Data licenses, permissions, consent restrictions and redistribution conditions have not been independently checked.
• Artifacts are referenced only; PDF/archive contents, dependency locks and bytes have not been inspected or executed.