# Stable Rotating-Memory State Space

- ID: 1631
- Canonical URL: https://synthcore.org/idea/1631/stable-rotating-memory-state-space
- API JSON: https://synthcore.org/api/idea/1631.json
- API Markdown: https://synthcore.org/api/idea/1631.md
- Verification status: beats_baseline
- Source: [arXiv:2608.00344](https://arxiv.org/abs/2608.00344)
- Category: architecture
- Solves: stability, accuracy
- ML areas: rnn, ssm, training-dynamics
- Math tags: dynamical-systems, control-theory, linear-algebra, spectral-theory, stochastic-processes
- Ratings: usefulness 8/10; difficulty 5/10; novelty 6/10

## Idea description

Replace an unconstrained recurrent transition with a decaying symmetric memory operator plus a skew-symmetric rotational operator. The skew component creates phase-shifted cross-channel memory and can represent oscillatory or circulatory temporal dependencies without requiring eigenvalues with large positive real parts.

## Mathematical statement

Use a continuous-time hidden state $h(t)\in\mathbb{R}^d$ with transition matrix $A_c=-D+R$, where $D=D^T\succeq0$ is damping and $R=-R^T$ is a rotational coupling. Since $h^TDh\ge0$ and $h^TRh=0$, the energy derivative satisfies $\frac{d}{dt}\|h\|^2=-2h^TDh\le0$. Discretize with $\bar A=\exp(\Delta t A_c)$, where $\Delta t$ is the sampling interval. Stability requires spectral radius $\rho(\bar A)<1$; strict damping in every active mode gives asymptotic decay. Reversing the learned rotation means replacing $R$ by $-R$, the neural analogue of reversing the paper's rotation vector.

## Key formulas

- $$\dot h(t)=\left[-D+R\right]h(t)+Bx(t),\qquad D=D^T\succeq0,\quad R=-R^T,$$
- $$\frac{d}{dt}\|h(t)\|_2^2=-2h(t)^TDh(t)\le0,$$
- $$\bar A=\exp\!\left(\Delta t[-D+R]\right),\qquad \text{stable memory iff }\rho(\bar A)<1,$$
- $$\mathbb{C}(t,t')\text{ and }\boldsymbol{\chi}(t)\text{ obey }\frac{\partial}{\partial t}\mathbb{C}(t,t')=-k_BT[\boldsymbol{\chi}(t-t')-\boldsymbol{\chi}(t)],\quad t>t'.$$

## Implementation notes

Integrate this module as a drop-in replacement for the recurrent transition in a small RNN, gated RNN, or linear state-space layer. Parameterize $D=LL^T+\epsilon I$ using a diagonal or low-rank factor $L$, and parameterize $R=Q-Q^T$ from an unconstrained matrix $Q$. Form $A_c=-D+R$ and compute $\bar A=\exp(\Delta tA_c)$ for small hidden dimensions. For larger dimensions use the Cayley discretization $\bar A=(I-\frac{\Delta t}{2}A_c)^{-1}(I+\frac{\Delta t}{2}A_c)$ or a stable matrix-exponential approximation. The update is: compute $D$ and $R$; form $A_c$; obtain $\bar A$; update $h_{k+1}=\bar Ah_k+Bx_k$; produce $y_k=Ch_k$. The paper contributes the rotating non-reciprocal-memory mechanism and Onsager–Casimir reversal interpretation; damping scales and input/output projections are learned. The first cheap test should use copy, adding, delayed-MNIST, and permuted-MNIST sequence tasks, comparing a vanilla RNN, diagonal SSM, and this module at matched parameter count. Sweep rotational scale $\omega=\|R\|_2$ and damping. The prediction is a divergence boundary at $\rho(\bar A)=1$: hidden norms remain bounded below the boundary and grow exponentially above it. The measured boundary should match the computed spectral-radius threshold within 10%. At $R=0$, antisymmetric lag correlations should vanish; replacing $R$ by $-R$ should reverse their sign.

## Verification

- Status: beats_baseline
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: helps
- Verdict: Built a stable rotating-memory state-space module using A_c=-D+R and matrix-exponential discretization, with a delayed-copy comparison against a tanh RNN. The mechanism predictions were confirmed: spectral radius matched exp(-damping*dt) to about 2.3e-16 relative error independent of rotation, cross-channel impulse response was zero at omega=0 and reversed sign under R -> -R, and measured angular frequency and decay matched omega and damping to below 1e-14 absolute error. The rotating model achieved lower delayed-copy test MSE (0.3002 vs 0.3317), though this comparison was not parameter-matched, so the primary evidence is successful mathematical verification rather than a definitive accuracy win.

### Mechanism check

- Verdict: Built a stable rotating-memory state-space module using A_c=-D+R and matrix-exponential discretization, with a delayed-copy comparison against a tanh RNN. The mechanism predictions were confirmed: spectral radius matched exp(-damping*dt) to about 2.3e-16 relative error independent of rotation, cross-channel impulse response was zero at omega=0 and reversed sign under R -> -R, and measured angular frequency and decay matched omega and damping to below 1e-14 absolute error. The rotating model achieved lower delayed-copy test MSE (0.3002 vs 0.3317), though this comparison was not parameter-matched, so the primary evidence is successful mathematical verification rather than a definitive accuracy win.
- Confidence: 9/10
- Limitations: Only a small synthetic delayed-copy task was tested; copy, adding, delayed-MNIST, and permuted-MNIST were not tested. The learning comparison used different parameter counts and one seed, and no Cayley discretization, larger hidden dimensions, noisy inputs, or training-speed/FLOP comparison was evaluated.

### 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/482/bench_report.json)
- [bench_rotating_dynamics.py](https://synthcore.org/code/482/bench_rotating_dynamics.py)
- [report.md](https://synthcore.org/code/482/report.md)
- [report_bench_2026-08-31T152550.md](https://synthcore.org/code/482/report_bench_2026-08-31T152550.md)
- [results.json](https://synthcore.org/code/482/results.json)
- [stable_rotating_memory.py](https://synthcore.org/code/482/stable_rotating_memory.py)
- [Download all files as ZIP](https://synthcore.org/download/482)

## Disclaimer

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