Research map / Probabilistic and scientific modeling / Variational and generative sampling
Autoencoders in Function Space
Justin Bunker, Mark Girolami, Hefin Lambley, Andrew M. Stuart, T. J. Sullivan
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 OU decoder noise (kappa=25) instead of Brownian motion noise (ablation) | FVAE · Brownian Dynamics | generative sample quality and autoencoding MSE convergence | Improved |
| use FAE with H^-1 data norm instead of FVAE with white decoder noise (ablation) | FAE · Dirac Distributions | training loss stability with resolution | Improved |
| raise encoder point ratio from 10% to 90% during training (ablation) | FAE · Navier-Stokes (viscosity 1e-4) | reconstruction MSE | Mixed |
Closest papers by meaning
- From Variational to Deterministic Autoencoders (ICLR 2020 · similarity 0.86)
- Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias (ICLR 2022 · similarity 0.86)
- Variational Autoencoding Neural Operators (ICML 2023 · similarity 0.85)
- On the Value of Infinite Gradients in Variational Autoencoder Models (NeurIPS 2021 · similarity 0.85)
- ControlVAE: Tuning, Analytical Properties, and Performance Analysis (TPAMI 2021 · similarity 0.85)
- Mechanistic Interpretability with Sparse Autoencoder Neural Operators (NeurIPS 2026 · similarity 0.84)
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.
