Research map / Probabilistic and scientific modeling / Variational and generative sampling
Gacs-Korner Common Information Variational Autoencoder
Michael Kleinman, Alessandro Achille, Stefano Soatto, Jonathan Kao
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 |
|---|---|---|---|
| use GK-VAE instead of a contrastive objective | GK-VAE · Rotated MNIST | rotation decoding from representation | Improved |
| larger VAE latent size than number of ground-truth factors (ablation) | GK-VAE · Common-3dshapes | common/unique separation | No clear effect |
| partition latents fed to each view-specific decoder (ablation) | GK-VAE · Common-3dshapes/dsprites | common/unique separation | No clear effect |
| introduce correlations between unique components (Case 2) (ablation) | GK-VAE · Common-dsprites/3dshapes | common/unique separation | No clear effect |
| large beta_u = 100 (ablation) | GK-VAE · Common-3dshapes | common/unique separation | No clear effect |
| increase frame gap t | GK-VAE · Sprites | common information (KL) | Hurt |
| change which factors are unique (viewpoint only; or size, scale, orientation) (ablation) | GK-VAE · Common-3dshapes/dsprites variants | factor separation | No clear effect |
Closest papers by meaning
- Information-Theoretic Generalization Bounds for VAEs: A Role of Encoder and Latent Variable (ICML 2026 · similarity 0.88)
- Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders (NeurIPS 2021 · similarity 0.88)
- Coupled Variational Autoencoder (ICML 2023 · similarity 0.87)
- Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables (NeurIPS 2025 · similarity 0.86)
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data (ICLR 2024 · similarity 0.86)
- $t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence (ICLR 2024 · similarity 0.86)
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.
