Research map / Probabilistic and scientific modeling / Variational and generative sampling
DELBO: Efficient Score Algorithm for Feature Selection on Latent Variables of VAE
Yiran Dong, Chuanhou Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| optimize decoder with ELBD-selected latent variables | VAE (mean-field) · MNIST | -ELBO: 69.3 -> 31.5 | Improved |
| optimize decoder with ELBD-selected latent variables | VAE (full-cov) · MNIST | -ELBO: 29.0 -> 5.7 | Improved |
| optimize decoder with ELBD-selected latent variables | CVAE (full-cov) · MNIST | -ELBO: 29.2 -> 4.2 | Improved |
| optimize decoder with ELBD-selected latent variables | IAF-VAE (mean-field) · MNIST | -ELBO: 18.44 -> 18.39 | No clear effect |
| optimize decoder with ELBD-selected latent variables | IAF-VAE (mean-field) · Fingers | -ELBO: 12.42 -> 12.35 | No clear effect |
| select latent variables with ELBD rather than Laplacian score | VAE (full-cov) · MNIST | -ELBO: 20.6 -> 5.7 | Improved |
| select latent variables with ELBD rather than Laplacian score | VAE (full-cov) · Hand Gestures | -ELBO: 107.6 -> 41.7 | Improved |
| select latent variables with ELBD rather than Fisher | VAE (full-cov) · MNIST | -ELBO: 5.9 -> 5.7 | Improved |
| optimize decoder with ELBD-selected latent variables | VAE (mean-field) · Brain | -ELBO: 695.9 -> 529.2 | Improved |
| optimize decoder with ELBD-selected latent variables | VAE (mean-field) · Yale | -ELBO: 355.2 -> 236.2 | Improved |
| optimize decoder with ELBD-selected latent variables | VAE (mean-field) · MNIST | L2: 40.5 -> 31.3 | Improved |
Closest papers by meaning
- On the Stability of Feature Selection Algorithms (JMLR 2018 · similarity 0.84)
- E2E-FS: An End-to-End Feature Selection Method for Neural Networks (TPAMI 2022 · similarity 0.84)
- A Probabilistic Derivation of LASSO and L12-Norm Feature Selections (AAAI 2019 · similarity 0.84)
- Feature Selection for Latent Factor Models (CVPR 2025 · similarity 0.84)
- Most Influential Subset Selection: Challenges, Promises, and Beyond (NeurIPS 2024 · similarity 0.83)
- SAND: One-Shot Feature Selection with Additive Noise Distortion (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
