EasyDeepLearn

VAE-based anomaly detection — advantages.

hard

Answer

  • VAE learns probabilistic latent space with p(x).
  • Anomaly score: (1) reconstruction error, (2) negative ELBO, (3) KL between q(zx)q(z \mid x) and prior.
  • Advantages over AE: probabilistic, calibrated uncertainty, generative — can synthesize plausible normals.
  • Weakness: still needs threshold tuning; failure mode: 'likelihood > uniform' issue (in-distribution mismatch on OOD data — Nalisnick et al. 2019).
Check yourself — multiple choice
  • Same as AE
  • VAE: reconstruction error or negative ELBO or KL(qp)\operatorname{KL}(q \mid \mid p) as anomaly score; probabilistic + calibrated; watch Nalisnick likelihood pitfall on OOD
  • Random
  • Not real

VAE anomaly: ELBO / recon error / KL; watch Nalisnick OOD pitfall.

#anomaly-detection#deep-learning

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions