# Subspace Neural Physics: Fast Data-Driven Interactive Simulation

*Source* · `src-holden-2019-subspace-neural-physics` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Daniel Holden, Bang Chi Duong, Sayantan Datta, Derek Nowrouzezahrai |
| venue | ACM SIGGRAPH/Eurographics Symposium on Computer Animation 2019 |
| date | 2019-07 |
| url | https://theorangeduck.com/page/subspace-neural-physics-fast-data-driven-interactive-simulation |
| doi | 10.1145/3309486.3340245 |
| accessed | 2026-10-24 |

## Notes

Ubisoft La Forge: network predicts dynamics in a PCA subspace of an offline cloth or deformable simulation; reported 300-5000x faster than the source simulation at small extra memory; not stated to have shipped.

## Backlinks (computed)

**cited by:** [Subspace neural physics and learned deformers](../technique/subspace-neural-physics.md)

## Citation

Daniel Holden, Bang Chi Duong, Sayantan Datta, Derek Nowrouzezahrai (2019-07). *Subspace Neural Physics: Fast Data-Driven Interactive Simulation*. ACM SIGGRAPH/Eurographics Symposium on Computer Animation 2019 https://theorangeduck.com/page/subspace-neural-physics-fast-data-driven-interactive-simulation

---
Provenance: created in run `2026-10-24-techniques-sim-math`.