Research map / Probabilistic and scientific modeling / Variational and generative sampling
Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
Naoya Takeishi, Alexandros Kalousis
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 |
|---|---|---|---|
| Add the full physics-integrated VAE regularizers | Physics-integrated VAE · Pendulum test | inferred ω MAE: 1.04 -> 0.229 | Improved |
| Add the full physics-integrated VAE regularizers | Physics-integrated VAE · Advection-diffusion test | inferred a MAE: 0.258 -> 0.00951 | Improved |
| Add the full physics-integrated VAE regularizers | Physics-integrated VAE · Pendulum test | reconstruction MAE: 0.370 -> 0.363 | Improved |
| Add the full physics-integrated VAE regularizers | Physics-integrated VAE · Advection-diffusion test | reconstruction MAE: 0.0404 -> 0.0437 | Hurt |
| Add the full physics-integrated VAE regularizers | Physics-integrated VAE · Human gait test | reconstruction error: 0.273 -> 0.259 | Improved |
| Add the PPC regularizer (α) (ablation) | NN+phys+reg · Pendulum and advection-diffusion test | inference MAE: 0.889 -> 0.229; 0.0444 -> 0.00951 | Improved |
| Add the physics data-augmentation regularizer R_DA,1 (β) (ablation) | NN+phys+reg · Pendulum and advection-diffusion test | inference MAE: 0.223 -> 0.229; 0.199 -> 0.00951 | Improved |
| Add the physics data-augmentation regularizer R_DA,2 (γ) (ablation) | NN+phys+reg · Pendulum and advection-diffusion test | inference MAE: 0.276 -> 0.229; 0.0548 -> 0.00951 | Improved |
| Add the full physics-integrated VAE regularizers | Physics-integrated VAE · Galaxy10 Disk, Edge-on, No Bulge | qualitative generation realism | Improved |
Closest papers by meaning
- From Variational to Deterministic Autoencoders (ICLR 2020 · similarity 0.88)
- Connections with Robust PCA and the Role of Emergent Sparsity in Variational Autoencoder Models (JMLR 2018 · similarity 0.88)
- A Geometric Perspective on Variational Autoencoders (NeurIPS 2022 · similarity 0.88)
- On the Value of Infinite Gradients in Variational Autoencoder Models (NeurIPS 2021 · similarity 0.87)
- Variational Autoencoders Pursue PCA Directions (by Accident) (CVPR 2019 · similarity 0.87)
- Variational Autoencoders with Jointly Optimized Latent Dependency Structure (ICLR 2019 · similarity 0.87)
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.
