# Coefficient-Space Neural Uncertainty Filter

- ID: 1010
- Canonical URL: https://synthcore.org/idea/1010/coefficient-space-neural-uncertainty-filter
- API JSON: https://synthcore.org/api/idea/1010.json
- API Markdown: https://synthcore.org/api/idea/1010.md
- Verification status: failed_benchmark
- Source: [arXiv:2607.16504](https://arxiv.org/abs/2607.16504)
- Category: dynamics
- Solves: accuracy, stability, speedup
- ML areas: world-model, rnn, rl, training-dynamics
- Math tags: stochastic-processes, probability, approximation-theory, linear-algebra, dynamical-systems
- Ratings: usefulness 8/10; difficulty 6/10; novelty 7/10

## Idea description

Replace an EKF or a large particle ensemble inside a neural world model with a fixed-order polynomial chaos representation of the latent state distribution. The transition network is evaluated under quadrature or sampled chaos variables, and Galerkin projection produces the next uncertainty coefficients directly; a coefficient-wise LMMSE update then assimilates observations without backpropagating through resampling.

## Mathematical statement

The paper starts from the Itô SDE $d\mathbf{x}(t)=\mathbf{f}(\mathbf{x}(t),t)dt+\mathbf{G}(\mathbf{x}(t),t)d\mathbf{w}(t)$, where $\mathbf{x}(t)\in\mathbb{R}^{d_x}$ is the stochastic state, $\mathbf{f}$ is the drift, $\mathbf{G}$ is the diffusion matrix, and $\mathbf{w}(t)$ is Brownian motion. Represent each state component with an orthonormal polynomial chaos basis $\{\Psi_\alpha(\boldsymbol{\xi})\}_{\alpha\in\mathcal{A}}$, where $\boldsymbol{\xi}$ contains standardized latent randomness and $\mathbb{E}[\Psi_\alpha\Psi_\beta]=\delta_{\alpha\beta}$: $\mathbf{x}\approx\sum_{\alpha\in\mathcal{A}}\mathbf{c}_\alpha\Psi_\alpha$. Here $\mathbf{c}_\alpha\in\mathbb{R}^{d_x}$ is a coefficient and $\alpha$ is a multi-index; $\mathbf{c}_0=\mathbb{E}[\mathbf{x}]$, and for orthonormal bases $\operatorname{Cov}(\mathbf{x})\approx\sum_{\alpha\neq0}\mathbf{c}_\alpha\mathbf{c}_\alpha^\top$. For timestep $\Delta t$, Euler-Maruyama gives $\mathbf{x}^+=\mathbf{x}+\mathbf{f}(\mathbf{x},t)\Delta t+\mathbf{G}(\mathbf{x},t)\sqrt{\Delta t}\,\boldsymbol{\eta}$, with standard normal process-noise vector $\boldsymbol{\eta}$. Galerkin projection gives $\mathbf{c}^+_\alpha=\mathbb{E}[\mathbf{x}^+\Psi_\alpha]=\mathbf{c}_\alpha+\Delta t\,\mathbb{E}[\mathbf{f}(\mathbf{x},t)\Psi_\alpha]+\sqrt{\Delta t}\,\mathbb{E}[\mathbf{G}(\mathbf{x},t)\boldsymbol{\eta}\Psi_\alpha]$. For observation $\mathbf{y}=\mathbf{h}(\mathbf{x})+\boldsymbol{\varepsilon}$, define $\mathbf{d}_\alpha=\mathbb{E}[\mathbf{h}(\mathbf{x})\Psi_\alpha]$, $\mathbf{P}_{xy}=\sum_{\alpha\neq0}\mathbf{c}_\alpha\mathbf{d}_\alpha^\top$, and $\mathbf{P}_{yy}=\sum_{\alpha\neq0}\mathbf{d}_\alpha\mathbf{d}_\alpha^\top+\mathbf{R}$, where $\mathbf{R}=\operatorname{Cov}(\boldsymbol{\varepsilon})$. The LMMSE gain is $\mathbf{K}=\mathbf{P}_{xy}\mathbf{P}_{yy}^{-1}$, followed by $\mathbf{c}_0^+=\mathbf{c}_0^-+\mathbf{K}(\mathbf{y}_{obs}-\mathbf{d}_0^-)$ and $\mathbf{c}_\alpha^+=\mathbf{c}_\alpha^- -\mathbf{K}\mathbf{d}_\alpha^-$ for $\alpha\neq0$. Superscripts $-$ and $+$ denote pre- and post-observation coefficients.

## Key formulas

- $$d\mathbf{x}(t)=\mathbf{f}(\mathbf{x}(t),t)dt+\mathbf{G}(\mathbf{x}(t),t)d\mathbf{w}(t)$$
- $$\mathbf{x}\approx\sum_{\alpha\in\mathcal{A}}\mathbf{c}_\alpha\Psi_\alpha(\boldsymbol{\xi}),\qquad \mathbb{E}[\Psi_\alpha\Psi_\beta]=\delta_{\alpha\beta},\qquad \operatorname{Cov}(\mathbf{x})\approx\sum_{\alpha\neq0}\mathbf{c}_\alpha\mathbf{c}_\alpha^\top$$
- $$\mathbf{c}^+_\alpha=\mathbf{c}_\alpha+\Delta t\,\mathbb{E}[\mathbf{f}(\mathbf{x},t)\Psi_\alpha]+\sqrt{\Delta t}\,\mathbb{E}[\mathbf{G}(\mathbf{x},t)\boldsymbol{\eta}\Psi_\alpha]$$
- $$\mathbf{K}=\mathbf{P}_{xy}\mathbf{P}_{yy}^{-1},\quad \mathbf{P}_{xy}=\sum_{\alpha\neq0}\mathbf{c}_\alpha\mathbf{d}_\alpha^\top,\quad \mathbf{P}_{yy}=\sum_{\alpha\neq0}\mathbf{d}_\alpha\mathbf{d}_\alpha^\top+\mathbf{R},\quad \mathbf{c}_0^+=\mathbf{c}_0^-+\mathbf{K}(\mathbf{y}_{obs}-\mathbf{d}_0^-),\quad \mathbf{c}_\alpha^+=\mathbf{c}_\alpha^- -\mathbf{K}\mathbf{d}_\alpha^-$$

## Implementation notes

Integrate this at the latent-state interface of a small neural world model or recurrent estimator. Let the latent state have dimension $D$, choose total polynomial order $p=2$ or $3$, and let $M=\binom{q+p}{p}$ coefficients be used for $q$ independent Gaussian chaos variables. Store a tensor `C` of shape `[M,B,D]`, with coefficient zero as the latent mean. Use a fixed tensor `Xi` of quadrature points or antithetic standard-normal samples and precompute the orthonormal Hermite matrix `Psi[m,alpha]`. At each transition, reconstruct `X[m]=sum_alpha C[alpha]*Psi[m,alpha]`, evaluate the neural dynamics `F=transition_net(X, action)`, and, if process noise is state dependent, evaluate `G`; form `Xnext=X+dt*F+sqrt(dt)*G*Eta`. Reproject with `Cnext[alpha]=sum_m w[m]*Xnext[m]*Psi[m,alpha]`, which implements the Galerkin formula. For an observation, evaluate `Y[m]=measurement_net(X[m])`, compute `Dcoef[alpha]=sum_m w[m]*Y[m]*Psi[m,alpha]`, construct `Pxy` and `Pyy` from the displayed sums, add diagonal jitter $\epsilon I$ to `Pyy`, solve for `K` rather than explicitly inverting it, and apply the coefficient-wise update. Backpropagate through reconstruction, transition evaluation, projection, and update; optionally train with negative log-likelihood and a coverage penalty. The math determines projection and LMMSE equations. Empirical choices are polynomial order, quadrature, noise covariance, and jitter. First test a 2D nonlinear pendulum or Lorenz-63 observation task with a GRU transition, comparing against a diagonal EKF and a 128-particle filter at matched transition-network evaluations. Measure one-step and long-horizon negative log-likelihood, RMSE, 90% interval coverage, coefficient-norm explosions, and wall-clock cost. Success is better calibration and accuracy than EKF with substantially fewer transition evaluations than particles.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: no_effect
- Verdict: Built a fixed-order Hermite PCE filter with Gauss-Hermite Galerkin projection and coefficient-wise LMMSE observation updates. The mechanism checks passed: degree-2/3 truncation errors vanished at matching order (about 1e-15), Parseval variance loss matched exactly, and the LMMSE post-update variance identity differed by 1.2e-16. In the nonlinear scalar toy task, PCE was slightly worse than EKF: RMSE 0.2670 vs 0.2637, NLL 0.0756 vs 0.0541, and 90% coverage 0.8806 vs 0.8986; it also used 48 versus 1 transition evaluations per step.

### Mechanism check

- Verdict: Built a fixed-order Hermite PCE filter with Gauss-Hermite Galerkin projection and coefficient-wise LMMSE observation updates. The mechanism checks passed: degree-2/3 truncation errors vanished at matching order (about 1e-15), Parseval variance loss matched exactly, and the LMMSE post-update variance identity differed by 1.2e-16. In the nonlinear scalar toy task, PCE was slightly worse than EKF: RMSE 0.2670 vs 0.2637, NLL 0.0756 vs 0.0541, and 90% coverage 0.8806 vs 0.8986; it also used 48 versus 1 transition evaluations per step.
- Confidence: 8/10
- Limitations: This MVP is scalar and uses a nonlinear toy filter rather than a neural world model or GRU. It does not compare against a particle filter, and additive process noise is approximated by variance inflation rather than represented with augmented independent chaos variables. Runtime and FLOP advantages were not established; the PCE quadrature implementation was substantially more expensive than the EKF in this setup.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.23785
- Paired wins: 2/8
- Benchmark verdict: no measurable effect

## Artifacts

- [bench_pce_dynamics.py](https://synthcore.org/code/180/bench_pce_dynamics.py)
- [bench_report.json](https://synthcore.org/code/180/bench_report.json)
- [pce_filter_experiment.py](https://synthcore.org/code/180/pce_filter_experiment.py)
- [report.md](https://synthcore.org/code/180/report.md)
- [report_bench_2026-08-30T193018.md](https://synthcore.org/code/180/report_bench_2026-08-30T193018.md)
- [results.json](https://synthcore.org/code/180/results.json)
- [Download all files as ZIP](https://synthcore.org/download/180)

## Disclaimer

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