# Zubov Invariant Head for Stable Latent Dynamics

- ID: 1650
- Canonical URL: https://synthcore.org/idea/1650/zubov-invariant-head-for-stable-latent-dynamics
- API JSON: https://synthcore.org/api/idea/1650.json
- API Markdown: https://synthcore.org/api/idea/1650.md
- Verification status: mech_ok_no_baseline
- Source: [arXiv:2608.01018](https://arxiv.org/abs/2608.01018)
- Category: dynamics
- Solves: stability, generalization
- ML areas: rnn, ssm, world-model, regularization
- Math tags: dynamical-systems, control-theory, functional-analysis, spectral-theory
- Ratings: usefulness 8/10; difficulty 6/10; novelty 7/10

## Idea description

Attach a scalar Zubov head to a neural ODE, state-space model, or recurrent world model and train it to be invariant under a discounted Koopman action. The head should be near one for trajectories attracted to the target equilibrium and near zero for states with large accumulated deviation, providing a long-horizon stability signal and an off-distribution failure detector.

## Mathematical statement

For a continuous system \(\dot{x}=f(x)\) with flow \(S_f^t(x)\), the domain of attraction is \(\mathbb{A}=\{x:\lim_{t\to\infty}S_f^t(x)=0\}\). Choose a nonnegative cost \(q(x)\), with \(q(0)=0\) and \(q(x)>0\) away from the equilibrium, and define \(u(x)=\exp[-\int_0^\infty q(S_f^s(x))\,ds]\). Splitting the integral at \(\Delta t\) gives the invariant relation \(u(x)=\exp[-\int_0^{\Delta t}q(S_f^s(x))ds]u(S_f^{\Delta t}(x))\). For a learned transition \(F_\theta\), define \(\mathcal{T}_\theta u(x)=\gamma_\theta(x)u(F_\theta(x))\), with \(\gamma_\theta(x)=\exp[-\Delta t q(x)]\) or a path-integral quadrature estimate. The RKHS construction in the paper makes the Zubov-Koopman operator spectrally contractive, \(\rho(\mathcal{T})<1\), after constant-function augmentation, so operator iteration converges.

## Key formulas

- $$\mathbb{A}=\left\{x\in\mathbb{X}:\lim_{t\to\infty}S_f^t(x)=0\right\},\qquad \dot{x}=f(x).$$
- $$u(x)=\exp\left[-\int_0^\infty q(S_f^s(x))\,ds\right],\qquad u(x)=\exp\left[-\int_0^{\Delta t}q(S_f^s(x))\,ds\right]u(S_f^{\Delta t}(x)).$$
- $$\mathcal{T}_\theta u(x)=\gamma_\theta(x)u(F_\theta(x)),\qquad \gamma_\theta(x)=\exp[-\Delta t q(x)],\qquad \rho(\mathcal{T}_\theta)<1.$$
- $$\mathcal{L}_{\mathrm{Z}}=\frac{1}{B}\sum_{i=1}^{B}\left[u_\phi(x_i)-\gamma_\theta(x_i)u_\phi(F_\theta(x_i))\right]^2+\lambda u_\phi(0)^2.$$

## Implementation notes

Use a neural ODE, RSSM, S4-like state-space model, or GRU world model with latent state \(z_t\) and transition \(z_{t+1}=F_\theta(z_t,a_t)\). Add an MLP scalar head \(u_\phi(z)\in(0,1)\), implemented with a sigmoid, and designate the target latent equilibrium \(z_*\). Set \(q(z)=\|z-z_*\|^2/(\sigma_q^2+\|z-z_*\|^2)\). For each minibatch state, compute \(z'_i=F_\theta(z_i,a_i)\), \(\gamma_i=\exp[-\Delta t q(z_i)]\), and minimize the ordinary prediction loss plus \(\mathcal{L}_{\mathrm{Z}}=B^{-1}\sum_i[u_\phi(z_i)-\gamma_i u_\phi(z'_i)]^2\). Add \(\lambda(u_\phi(z_*)-1)^2\). During warmup, stop gradients through \(F_\theta\) in the Zubov term to avoid trivial co-adaptation. The paper supplies the invariant relation and RKHS spectral-contraction mechanism; estimate the learned operator radius empirically by power iteration on sampled transitions or by measuring successive probe-function norms. First test a two-layer GRU on damped nonlinear-pendulum trajectories, comparing ordinary training with Zubov regularization. The prediction is geometric decay \(\|\mathcal{T}^kg-u\|\lesssim C\rho^k\), with log-error slope \(\log\hat\rho\), and a sharp rollout-stability change near \(\hat\rho=1\). The measured slope should agree with \(\log\hat\rho\) within 20 percent.

## Verification

- Status: mech_ok_no_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: harms
- Verdict: Built a reproducible Zubov invariant-head experiment in experiment.py. The mechanism manifested in the toy checks: the trapezoidal invariant residual scaled as dt^2.994 versus the predicted dt^3, shell contraction matched exp(-dt q(r)) with maximum absolute error 0, and gamma scaling approached q(x)=0.6098 with 0.3%-2.4% relative error. However, the mini-experiment showed no prediction or rollout win, and the learned head did not meaningfully separate equilibrium from a far state, so this validates the mechanism but not practical benefit.

### Mechanism check

- Verdict: Built a reproducible Zubov invariant-head experiment in experiment.py. The mechanism manifested in the toy checks: the trapezoidal invariant residual scaled as dt^2.994 versus the predicted dt^3, shell contraction matched exp(-dt q(r)) with maximum absolute error 0, and gamma scaling approached q(x)=0.6098 with 0.3%-2.4% relative error. However, the mini-experiment showed no prediction or rollout win, and the learned head did not meaningfully separate equilibrium from a far state, so this validates the mechanism but not practical benefit.
- Confidence: 8/10
- Limitations: Only a small one-step MLP transition experiment was run rather than a true two-layer GRU or neural ODE. The transition was detached in the Zubov term, no off-distribution or unstable trajectories were evaluated, and there were no repeated seeds, hyperparameter sweeps, or statistically powered comparisons.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.0081
- Paired wins: 0/8
- Benchmark verdict: idea worse (significant)

## Artifacts

- [bench_report.json](https://synthcore.org/code/544/bench_report.json)
- [bench_zubov.py](https://synthcore.org/code/544/bench_zubov.py)
- [experiment.py](https://synthcore.org/code/544/experiment.py)
- [report.md](https://synthcore.org/code/544/report.md)
- [report_bench_2026-08-31T172626.md](https://synthcore.org/code/544/report_bench_2026-08-31T172626.md)
- [results.json](https://synthcore.org/code/544/results.json)
- [Download all files as ZIP](https://synthcore.org/download/544)

## Disclaimer

AI-generated research hypothesis, automatically tested. Not peer-reviewed.