Research map / Probabilistic and scientific modeling / Variational and generative sampling
A Contrastive Learning Approach for Training Variational Autoencoder Priors
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 |
|---|---|---|---|
| re-weight prior samples with NCP | hierarchical VAE prior · MMD to aggregate posterior, 10 groups | MMD: 0.08 -> 0.06 | Helped |
| re-weight prior samples with NCP | hierarchical VAE prior · MMD to aggregate posterior, 5 groups | MMD: 0.002 -> 0.002 | No clear effect |
| use NCP instead of SNIS for sample generation | MNIST VAE · batch of 1 image | time (sec): 0.004 -> 0.001 | Helped |
| use NCP instead of SNIS for sample generation | MNIST VAE · 128 proposals | memory (MB): 275 -> 543 | Hurt |
| increase latent dimension from 50 to 1000 (ablation) | NCP single-group MNIST model · MNIST | NLL lower bound: 82.82 -> 83.54 | Hurt |
Closest papers by meaning
- Variational Autoencoder with Implicit Optimal Priors (AAAI 2019 · similarity 0.91)
- Trading Information between Latents in Hierarchical Variational Autoencoders (ICLR 2023 · similarity 0.91)
- From Variational to Deterministic Autoencoders (ICLR 2020 · similarity 0.91)
- MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders (ICLR 2019 · similarity 0.91)
- Explicitly Minimizing the Blur Error of Variational Autoencoders (ICLR 2023 · similarity 0.91)
- Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders (ICLR 2024 · similarity 0.90)
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.