# Feedback-preconditioned recurrent dynamics

- ID: 770
- Canonical URL: https://synthcore.org/idea/770/feedback-preconditioned-recurrent-dynamics
- API JSON: https://synthcore.org/api/idea/770.json
- API Markdown: https://synthcore.org/api/idea/770.md
- Verification status: failed_benchmark
- Source: [arXiv:2607.11835](https://arxiv.org/abs/2607.11835)
- Category: dynamics
- Solves: stability, accuracy, speedup
- ML areas: rnn, ssm, training-dynamics
- Math tags: control-theory, dynamical-systems, linear-algebra, functional-analysis
- Ratings: usefulness 7/10; difficulty 5/10; novelty 5/10

## Idea description

Reparameterize a recurrent or state-space layer so that its hidden-state update contains an explicit stabilizing feedback controller, while the neural network learns only a residual control in the feedback coordinates. Choose K to reduce finite-horizon state-propagation amplification, suppressing exploding hidden states and gradients on long sequences.

## Mathematical statement

The paper replaces the constraint operator [A,-B] by [A-BK,-B], where A is the state operator, B maps controls into the state equation, and K maps states to feedback controls. The coordinate substitution is u=Kx+v, so v is the residual control and the physical control is u. If A is surjective, the transformed constraint remains surjective and the transformed optimization problem is equivalent to the original. For the discrete scalar system x_{k+1}=a x_k+u_k, the original finite-horizon control-to-state matrix T_N has entries a^{i-j} for i>=j, and its norm is O(1) for a<1, O(N) for a=1, and O(a^N) for a>1. Under u_k=Kx_k+v_k, the closed-loop multiplier is a_cl=a+K for this update convention; in the paper's operator convention it is A-BK. For a matrix recurrence h_{t+1}=Ah_t+Bu_t, use A_cl=A+BK and the block map T_N(A_cl,B)_{ij}=A_cl^{i-j}B for i>=j. Choosing rho(A_cl)<1 makes long-horizon propagation bounded instead of exponentially amplified.

## Key formulas

- $$[\widetilde{\mathcal A},-\mathcal B]\coloneqq[\mathcal A-\mathcal B\mathcal K,-\mathcal B]$$
- $$\begin{bmatrix}x\\u\end{bmatrix}=\begin{bmatrix}I&0\\\mathcal K&I\end{bmatrix}\begin{bmatrix}x\\v\end{bmatrix},\qquad u=\mathcal Kx+v$$
- $$\sigma_0=\|\mathcal C\mathcal A^{-1}\mathcal B\|=\|\mathcal A^{-1}\|=\begin{cases}\mathcal O(1)&a<1,\\\mathcal O(N)&a=1,\\\mathcal O(a^N)&a>1,\end{cases}$$
- $$\mathcal T_N(A_{\mathrm{cl}},B)_{ij}=\begin{cases}A_{\mathrm{cl}}^{\,i-j}B,&i\ge j,\\0,&i<j,\end{cases}\qquad A_{\mathrm{cl}}=A+BK,\qquad u_t=Kh_t+v_t$$

## Implementation notes

Integrate this into the recurrent transition of a vanilla RNN or linear state-space model. Keep hidden dimension d and input map B, but replace h_{t+1}=phi(Ah_t+Bu_t+c_t) with h_{t+1}=phi(A_cl h_t+Bv_t+c_t), where A_cl=A+BK and v_t is produced by the existing neural input/nonlinear pathway. Initialize A from the baseline model, then choose K so A_cl has target spectral radius rho_target, for example by setting K=-A+rho_target Q with Q orthogonal, or learn K with a penalty on an estimated spectral radius. Use pseudocode: `h=init(); for t in range(T): v=control_net(x[t],h); h=phi(A_cl@h+B@v+b); y=readout(h)`. If the original model exposes a physical control, reconstruct it as u_t=K h_t+v_t. Estimate amplification by power iteration on the implicit map from a length-N sequence v to the resulting states: forward-propagate T_N q, apply the transpose recurrence backward, normalize, and record the dominant singular-value estimate. The paper supplies the feedback transformation and block structure; empirical measurements are the singular-value estimate, hidden-state RMS, and gradient norms. First test a 1-2 layer tanh RNN on adding, copy-memory, and permuted-MNIST at lengths 128, 512, and 2048. Compare with the identical baseline, orthogonal initialization, and spectral-radius clipping. Success means bounded hidden and gradient RMS, fewer NaNs, faster loss decrease at equal FLOPs, and less accuracy degradation as sequence length increases.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: harms
- Verdict: Built a scalar feedback-preconditioned recurrent experiment with u=Kh+v, verifying numerically that the transformed multiplier is exactly a_cl=a+K with maximum error 4.4e-16. Finite-horizon operator sweeps confirmed the predicted stable, critical, and unstable regimes: observed terminal norm ratios were 1.015 versus predicted 1, 1.992 versus 2, and 445.815 versus 445.792. Forced-state RMS fell from 93,760 at a_cl=1.1 to 1.66 at 0.8 and 1.16 at 0.5; the tiny training test also reduced final loss and late gradient RMS, so the mechanism manifested.

### Mechanism check

- Verdict: Built a scalar feedback-preconditioned recurrent experiment with u=Kh+v, verifying numerically that the transformed multiplier is exactly a_cl=a+K with maximum error 4.4e-16. Finite-horizon operator sweeps confirmed the predicted stable, critical, and unstable regimes: observed terminal norm ratios were 1.015 versus predicted 1, 1.992 versus 2, and 445.815 versus 445.792. Forced-state RMS fell from 93,760 at a_cl=1.1 to 1.66 at 0.8 and 1.16 at 0.5; the tiny training test also reduced final loss and late gradient RMS, so the mechanism manifested.
- Confidence: 9/10
- Limitations: The mini-experiment used a scalar linear recurrence and an online sum task rather than nonlinear multidimensional RNNs, copy-memory, adding, or permuted-MNIST. It did not compare orthogonal initialization, spectral-radius clipping, FLOPs, accuracy across multiple sequence lengths, or multiple random seeds; the baseline and feedback models use different fixed recurrent multipliers by design.

### 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_feedback.py](https://synthcore.org/code/316/bench_feedback.py)
- [bench_report.json](https://synthcore.org/code/316/bench_report.json)
- [experiment.py](https://synthcore.org/code/316/experiment.py)
- [report.md](https://synthcore.org/code/316/report.md)
- [report_bench_2026-08-31T010334.md](https://synthcore.org/code/316/report_bench_2026-08-31T010334.md)
- [results.json](https://synthcore.org/code/316/results.json)
- [Download all files as ZIP](https://synthcore.org/download/316)

## Disclaimer

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