# Cyclic Multirate Neural State Space

- ID: 623
- Canonical URL: https://synthcore.org/idea/623/cyclic-multirate-neural-state-space
- API JSON: https://synthcore.org/api/idea/623.json
- API Markdown: https://synthcore.org/api/idea/623.md
- Verification status: beats_baseline
- Source: [arXiv:2607.09194](https://arxiv.org/abs/2607.09194)
- Category: architecture
- Solves: stability, accuracy, sample-efficiency
- ML areas: rnn, ssm, world-model
- Math tags: dynamical-systems, control-theory, spectral-theory, linear-algebra
- Ratings: usefulness 7/10; difficulty 5/10; novelty 6/10

## Idea description

Replace interpolation of heterogeneous sensor streams by a phase-indexed recurrent or state-space network with period M, where M is the least common multiple of the sensor sampling periods. The network applies a distinct transition for each phase while using a fixed cyclic phase update, preserving timing structure and allowing missing observations to enter only when their phase-specific sensor is available.

## Mathematical statement

For phase r in {0,...,M-1}, let h_t in R^d be the latent state, u_t the available input vector, and f_{theta,r} the transition used at phase r. The cyclic model is h_{t+1}=f_{theta,r_t}(h_t,u_t), r_{t+1}=(r_t+1) mod M, with observation model y_t=g_{phi,r_t}(h_t). In the linear case this is x(k+1)=A_k x(k)+B_k u(k), y(k)=C_k x(k)+D_k u(k), where all matrices repeat every M steps. A sufficient local contraction condition is that the Jacobian product over one cycle has norm below one: ||J_{M-1}...J_0||_2 <= rho < 1, where J_r is the Jacobian of f_{theta,r} with respect to h. This gives exponential decay of perturbations at cycle boundaries.

## Key formulas

- $$h_{t+1}=f_{\theta,r_t}(h_t,u_t),\qquad y_t=g_{\phi,r_t}(h_t),\qquad r_{t+1}=(r_t+1)\bmod M.$$
- $$\begin{bmatrix}h_{t+1}\\y_t\end{bmatrix}=\begin{bmatrix}A_{r_t}&B_{r_t}\\C_{r_t}&D_{r_t}\end{bmatrix}\begin{bmatrix}h_t\\u_t\end{bmatrix},\qquad A_{r+M}=A_r.$$
- $$\left\|J_{M-1}J_{M-2}\cdots J_0\right\|_2\leq\rho<1,\qquad J_r=\frac{\partial f_{\theta,r}}{\partial h},$$
- $$\|\delta h_{qM}\|_2\leq\rho^q\|\delta h_0\|_2.$$

## Implementation notes

1. Integration point: implement a recurrent, S4-like, or small neural state-space model whose transition receives an integer phase r and a sensor-availability mask. Create M phase-specific transition heads f_r, using a shared backbone plus a low-rank phase embedding when M is large. At each physical time step, feed only measurements that are actually present; do not forward-fill missing sensor values. 2. Pseudocode: initialize h and r; for each t, construct z=[u_t, availability_mask_t, phase_embedding(r)]; compute h_new=f_r(h,z); predict y_hat=g_r(h_new); accumulate loss only for observed outputs; set r=(r+1) mod M. Estimate the Jacobian product over each M-step window using automatic differentiation and add a penalty when its spectral norm exceeds a target rho. 3. Computed versus estimated: M and phase assignments are computed exactly from sensor periods; Jacobians and their product norm are estimated on minibatch trajectories; rho is a chosen contraction target. 4. First cheap experiment: train on a synthetic linear periodically time-varying system with M=3 and randomly missing outputs, comparing interpolation+GRU, a phase-blind GRU, and this model. Sweep recurrent gain or spectral-normalization scale and measure long-horizon rollout error and perturbation growth. The predicted signature is a stability boundary near ||J_2J_1J_0||_2=1. Below the boundary, perturbations should decay approximately as rho^q, with measured log-decay slope agreeing with log(rho) within 20%.

## Verification

- Status: beats_baseline
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: helps
- Verdict: Built a deterministic cyclic linear state-space verification and a small multirate forecasting comparison. The predicted contraction boundary gamma*=0.941036 for M=3 was observed at cycle norm 1.0; measured log-decay slopes matched log cycle norm essentially exactly across the sweep. Period scaling also matched Lambda^(-1/M) for M=2..5, and noncommuting transitions showed phase-order sensitivity. However, phase-aware forecasting MSE (0.071355) was slightly worse than phase-blind GRU-like linear recurrence (0.071331) and interpolation baseline (0.071330), so no practical accuracy win was demonstrated.

### Mechanism check

- Verdict: Built a deterministic cyclic linear state-space verification and a small multirate forecasting comparison. The predicted contraction boundary gamma*=0.941036 for M=3 was observed at cycle norm 1.0; measured log-decay slopes matched log cycle norm essentially exactly across the sweep. Period scaling also matched Lambda^(-1/M) for M=2..5, and noncommuting transitions showed phase-order sensitivity. However, phase-aware forecasting MSE (0.071355) was slightly worse than phase-blind GRU-like linear recurrence (0.071331) and interpolation baseline (0.071330), so no practical accuracy win was demonstrated.
- Confidence: 9/10
- Limitations: The practical comparison is a tiny linear recurrence proxy rather than trained GRU/neural state-space models, and it does not measure FLOPs, wall-clock speed, learned Jacobian penalties, or real heterogeneous sensor datasets. The exact mechanism verification uses constructed linear systems, so it establishes the mathematical signature rather than generalization to nonlinear models.

### Practical benchmark

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

## Artifacts

- [bench_report.json](https://synthcore.org/code/280/bench_report.json)
- [experiment.py](https://synthcore.org/code/280/experiment.py)
- [report.md](https://synthcore.org/code/280/report.md)
- [report_bench_2026-08-31T000200.md](https://synthcore.org/code/280/report_bench_2026-08-31T000200.md)
- [results.json](https://synthcore.org/code/280/results.json)
- [stage2_bench.py](https://synthcore.org/code/280/stage2_bench.py)
- [Download all files as ZIP](https://synthcore.org/download/280)

## Disclaimer

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