Skip to content

Variational Inference (VI)

Definition
AI-generated

Variational inference approximates an intractable posterior distribution by optimizing a simpler family of distributions, typically by maximizing a lower bound on the marginal likelihood (evidence).

Topics
Bayesian statistics Machine learning concepts
Related
Bayesian Statistics Posterior Distribution Variational Autoencoder (VAE)

Why it matters in GWAS

Large-scale fine-mapping, hierarchical LD models, and deep generative models in single-cell genomics often report variational rather than exact MCMC posteriors; understanding VI clarifies what is approximate in those uncertainty estimates.

Example usage

"Downstream interpretation uses Variational Inference (VI) to connect statistical evidence with biological context."

Bayesian Statistics Posterior Distribution Variational Autoencoder (VAE)
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Blei DM, Kucukelbir A, McAuliffe JD. (2017). Variational inference: a review for statisticians. J Am Stat Assoc.
  • Li Z, Zhou X. (2025). Towards improved fine-mapping of candidate causal variants. Nat Rev Genet. https://doi.org/10.1038/s41576-025-00869-4
← Variational Autoencoder (VAE) Variant Call Format (VCF) →

Last updated (UTC · Git history)