Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational Laplace Autoencoders
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Iterative posterior mode updates with full-covariance Gaussian posterior (VLAE) instead of VAE amortized diagonal Gaussian | VAE encoder (small net) · MNIST, Omniglot, Fashion-MNIST, SVHN, CIFAR10, binarized MNIST | log-likelihood | Helped |
| Increase number of posterior update steps T from 1 to 8 (ablation) | VLAE (small net) · small net Gaussian output datasets | log-likelihood | Mixed |
| Increase number of ReLU-network flows/updates on bigger networks (ablation) | VLAE and baselines (big net) · big net, all datasets | log-likelihood | Hurt |
| Householder Flow posterior (VAE+HF) vs. plain VAE | VAE · small net, Gaussian output | log-likelihood | Mixed |
| Semi-amortized gradient-based updates of variational parameters (SA-VAE) | VAE · small net, Gaussian output | log-likelihood | No clear effect |
| Semi-amortized gradient updates (SA-VAE) in big networks | VAE · big net, all datasets | log-likelihood | Hurt |
Closest papers by meaning
- Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders (CVPR 2022 · similarity 0.92)
- InfoVAE: Balancing Learning and Inference in Variational Autoencoders (AAAI 2019 · similarity 0.92)
- Semi-Amortized Variational Autoencoders (ICML 2018 · similarity 0.91)
- Variational Autoencoders with Jointly Optimized Latent Dependency Structure (ICLR 2019 · similarity 0.91)
- Recursive Inference for Variational Autoencoders (NeurIPS 2020 · similarity 0.91)
- Variational Learning of Fractional Posteriors (ICML 2025 · similarity 0.89)
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.