# Residual-to-State Update Throttle

- ID: 2027
- Canonical URL: https://synthcore.org/idea/2027/residual-to-state-update-throttle
- API JSON: https://synthcore.org/api/idea/2027.json
- API Markdown: https://synthcore.org/api/idea/2027.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.09030](https://arxiv.org/abs/2608.09030)
- Category: dynamics
- Solves: stability, generalization
- ML areas: optimizer, training-dynamics, scheduler
- Math tags: control-theory, dynamical-systems, optimization, linear-algebra
- Ratings: usefulness 7/10; difficulty 4/10; novelty 7/10

## Idea description

Add a closed-loop scalar gain that throttles a neural-network update when the observed loss residual is inconsistent with the available masked-gradient geometry. This converts the paper's ISS-style residual-to-parameter boundedness idea into a trust-region optimizer that permits aggressive updates during recurrent excitation but freezes weakly observed or contradictory directions.

## Mathematical statement

Let \(g_t\) be the observed minibatch gradient, \(u_t=B_t^{-1}g_t\) the observability-preconditioned direction, and \(r_t\) the vector of observed prediction residuals. Define the excitation energy \(q_t=\operatorname{tr}(G_t)\), where \(G_t=J_t^\top J_t\). Form the mismatch ratio \(\delta_t=\|r_t\|_2/(\sqrt{q_t}+\varepsilon)\), with \(\varepsilon>0\) preventing division by zero. Choose a bounded gain \(a_t\in[0,1]\) using \(a_t=\min\{1,\kappa/(\delta_t+\varepsilon)\}\), where \(\kappa>0\) is a design threshold, and update \(\theta_{t+1}=\theta_t-\eta a_tu_t\). Bounded mismatch then acts as a bounded forcing term in an ISS-like parameter-error inequality.

## Key formulas

- $$u_t=B_t^{-1}g_t,\qquad q_t=\operatorname{tr}(G_t),\qquad G_t=J_t^\top J_t,$$
- $$\delta_t=\frac{\|r_t\|_2}{\sqrt{q_t}+\varepsilon},\qquad a_t=\min\left\{1,\frac{\kappa}{\delta_t+\varepsilon}\right\},$$
- $$\theta_{t+1}=\theta_t-\eta a_tB_t^{-1}g_t,$$
- $$\|e_t\|\lesssim C\rho^{\lfloor t/W\rfloor}\|e_0\|+\frac{C}{1-\rho}\sup_i\|d_i\|,$$

## Implementation notes

Place the throttle between gradient computation and the optimizer update, after applying the masked observability preconditioner or a standard diagonal preconditioner. For each minibatch, compute predictions using observed inputs, retain the residual vector \(r=y-f_\theta(Mx)\), estimate \(q=\operatorname{tr}(J^\top J)\) with Hutchinson probes \(q\approx m^{-1}\sum_s\|Jz_s\|^2\), and calculate \(\delta=\|r\|/(\sqrt q+\varepsilon)\). Set \(a=\min(1,\kappa/(\delta+\varepsilon))\), multiply the preconditioned gradient by \(a\), optionally clip for numerical safety, and update parameters. The paper motivates the residual-to-state and ISS construction; constants \(C\), \(\rho\), and \(W\) should be estimated from trajectories rather than assumed known. Start with synthetic linear regression using a two-layer MLP whose true parameter is known. Impose alternating masks that hide each feature for 10-50 steps, and compare SGD, Adam, and the throttled method at learning rates near the divergence threshold. Log \(a_t\), parameter error, and residual. The quantitative prediction is a sharp reduction in parameter-error spikes whenever \(\delta_t>\kappa\), with error settling to a plateau proportional to the empirical maximum mismatch. Under recurrent excitation, the error envelope should decay geometrically between mask transitions rather than grow without bound.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: inconclusive
- Verdict: Built a deterministic residual-to-state throttle for masked linear regression, with exact gradient scaling and scalar stability checks. The predicted gain boundary a<1 occurred at residual norm κ√q with 0.06% relative sweep error; in the throttled regime, residual_norm·a/√q matched κ to about 4e-9. Plain scalar GD diverged for η>2 while throttled updates remained bounded in all tested cases. The mini-experiment showed the idea improved final error over SGD at η=0.24 (0.209 vs 0.353) and prevented instability, but was worse at η=0.08 because its mean gain was only 0.066, so this is a mechanism win and promising stability signal, not a universal optimization win.

### Mechanism check

- Verdict: Built a deterministic residual-to-state throttle for masked linear regression, with exact gradient scaling and scalar stability checks. The predicted gain boundary a<1 occurred at residual norm κ√q with 0.06% relative sweep error; in the throttled regime, residual_norm·a/√q matched κ to about 4e-9. Plain scalar GD diverged for η>2 while throttled updates remained bounded in all tested cases. The mini-experiment showed the idea improved final error over SGD at η=0.24 (0.209 vs 0.353) and prevented instability, but was worse at η=0.08 because its mean gain was only 0.066, so this is a mechanism win and promising stability signal, not a universal optimization win.
- Confidence: 9/10
- Limitations: The main mini-experiment used exact q for a linear model rather than Hutchinson Jacobian estimates or a two-layer MLP. It did not test large neural networks, wall-clock/FLOP overhead, realistic observability preconditioners B, noisy/nonlinear residual geometry, or longer recurrent-excitation trajectories. Adam was included only as a small comparison and was not hyperparameter-tuned.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.58435
- Paired wins: 6/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_report.json](https://synthcore.org/code/820/bench_report.json)
- [bench_runner.py](https://synthcore.org/code/820/bench_runner.py)
- [experiment.py](https://synthcore.org/code/820/experiment.py)
- [report.md](https://synthcore.org/code/820/report.md)
- [report_bench_2026-09-01T111806.md](https://synthcore.org/code/820/report_bench_2026-09-01T111806.md)
- [results.json](https://synthcore.org/code/820/results.json)
- [sweep_results.json](https://synthcore.org/code/820/sweep_results.json)
- [sweeps.py](https://synthcore.org/code/820/sweeps.py)
- [Download all files as ZIP](https://synthcore.org/download/820)

## Disclaimer

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