🛰️ Daily AI Frontier
‹ back to 2026-07-16

RTS Smoother-Guided Learning of Physics-Based Neural Differential Models

Research Physics-Informed ML

Ranking

Overall 68
Content 80
Popularity 41

Observed public metrics from 1 member.

Merged summary

TL;DR - A hybrid neural–physics framework that learns unknown parts of an ODE system from partial, noisy measurements by alternating between RTS-smoother state estimation and neural-network parameter fitting. It matters because it recovers missing dynamics while preserving interpretable mechanistic structure.

  • Keeps known ODE terms explicit and represents unknown terms with a neural network, retaining mechanistic interpretability.
  • Uses a two-stage iterative scheme: (1) infer latent states via a Rauch–Tung–Striebel smoother with parameters fixed, (2) fit NN parameters via backpropagation on the smoothed trajectories, repeating until convergence.
  • Designed for partial state observation, where only a subset of variables are measured and some equations are unknown.
  • Evaluated on linear, nonlinear, and stiff benchmark systems, reporting improved latent-state reconstruction and long-horizon prediction.

Sources (1)

RTS Smoother-Guided Learning of Physics-Based Neural Differential Models

arXiv cs.LG Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus 2026-07-16 arXiv:2607.15180
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-10 14:23:25.032644 UTC

TL;DR - A hybrid neural–physics framework that learns unknown parts of an ODE system from partial, noisy measurements by alternating between RTS-smoother state estimation and neural-network parameter fitting. It matters because it recovers missing dynamics while preserving interpretable mechanistic structure.

  • Keeps known ODE terms explicit and represents unknown terms with a neural network, retaining mechanistic interpretability.
  • Uses a two-stage iterative scheme: (1) infer latent states via a Rauch–Tung–Striebel smoother with parameters fixed, (2) fit NN parameters via backpropagation on the smoothed trajectories, repeating until convergence.
  • Designed for partial state observation, where only a subset of variables are measured and some equations are unknown.
  • Evaluated on linear, nonlinear, and stiff benchmark systems, reporting improved latent-state reconstruction and long-horizon prediction.
item →