# Concurrent-Learning Leak Calibration

- ID: 1913
- Canonical URL: https://synthcore.org/idea/1913/concurrent-learning-leak-calibration
- API JSON: https://synthcore.org/api/idea/1913.json
- API Markdown: https://synthcore.org/api/idea/1913.md
- Verification status: mech_ok_no_baseline
- Source: [arXiv:2608.06840](https://arxiv.org/abs/2608.06840)
- Category: dynamics
- Solves: stability, accuracy
- ML areas: ssm, rnn, training-dynamics, optimizer
- Math tags: control-theory, dynamical-systems, optimization, linear-algebra
- Ratings: usefulness 7/10; difficulty 5/10; novelty 7/10

## Idea description

Replace a fixed leak coefficient in a continuous-time SSM or leaky RNN by an online estimate learned from current and replayed hidden-state transitions. The estimator exploits the scalar nature of each decay parameter: a single transition with a nonzero hidden-state regressor is sufficient for exponential identification in the noiseless model, without requiring persistent excitation from the whole sequence.

## Mathematical statement

For one SSM coordinate, assume the transition obeys \(\dot{x}(t)=-a x(t)+b u(t)\), where \(x\) is the hidden state, \(u\) is the input, \(b\) is known or separately estimated, and the unknown leak rate satisfies \(a>0\). Define \(y(t)=\dot{x}(t)-b u(t)\), giving \(y(t)=-a x(t)\). With stored samples \((x_j,y_j)\), define residuals \(e(t)=y(t)+\hat a(t)x(t)\) and \(e_j=y_j+\hat a(t)x_j\). The concurrent-learning estimator is \(\dot{\hat a}=-\gamma[x(t)e(t)+\sum_jx_j e_j]\), with \(\gamma>0\). For parameter error \(\tilde a=\hat a-a\), the noiseless error equation is \(\dot{\tilde a}=-\gamma[x(t)^2+\sum_jx_j^2]\tilde a\). If one stored sample has \(x_j\ne0\), then \(I_*:=\sum_jx_j^2>0\) and \(|\tilde a(t)|\le|\tilde a(0)|e^{-\gamma I_*t}\). Projection onto \([a_{\min},a_{\max}]\), with \(a_{\min}>0\), preserves a contractive hidden transition and gives sensitivity decay bounded by \(e^{-a_{\min}t}\).

## Key formulas

- $$\dot{x}(t)=-a x(t)+b u(t),\qquad y(t):=\dot{x}(t)-b u(t)=-a x(t).$$
- $$\dot{\hat a}=-\gamma\left[x(t)\big(y(t)+\hat a x(t)\big)+\sum_{j=1}^{M}x_j\big(y_j+\hat a x_j\big)\right],\qquad \hat a\leftarrow\Pi_{[a_{\min},a_{\max}]}(\hat a).$$
- $$\dot{\tilde a}=-\gamma\left(x(t)^2+\sum_{j=1}^{M}x_j^2\right)\tilde a,\qquad |\tilde a(t)|\le |\tilde a(0)|e^{-\gamma I_*t},\quad I_*:=\sum_{j=1}^{M}x_j^2>0.$$
- $$\left|\frac{\partial x(t)}{\partial x(0)}\right|=e^{-\int_0^t\hat a(s)\,ds}\le e^{-a_{\min}t}\quad\text{when }\hat a(s)\ge a_{\min}>0.$$

## Implementation notes

Integrate the method at the recurrent or SSM transition level. Use a diagonal continuous-time layer \(\dot{x}=-\hat A x+B u\), initially with one scalar leak parameter shared by all hidden coordinates so the mechanism is easy to isolate. Discretize with Euler for the first prototype or use the exact diagonal transition \(x_{t+1}=e^{-\hat A\Delta t}x_t+\hat A^{-1}(I-e^{-\hat A\Delta t})Bu_t\). At each step, estimate \(y_t=(x_{t+1}-x_t)/\Delta t-bu_t\), form the current residual \(r_t=y_t+\hat a x_t\), retrieve stored pairs \((x_j,y_j)\), form \(r_j=y_j+\hat a x_j\), and update \(\hat a\leftarrow\hat a-\eta_a\gamma[x_t r_t+\sum_jx_jr_j]\). Project after every update to \([a_{\min},a_{\max}]\). Store a transition when \(|x_t|\) exceeds a threshold; retain the \(M\) samples with largest \(x_j^2\) or highest estimated signal-to-noise ratio. The paper supplies the concurrent-learning estimator and exponential error mechanism; the implementation must estimate derivatives from discrete noisy transitions and should stop-gradient through replay targets initially. First test a one-dimensional leaky SSM on the copy task and adding task, comparing fixed leak, current-sample-only adaptation, and concurrent learning. Log \(I_* =\sum_jx_j^2\) and parameter error. The quantitative prediction is that the noiseless semilog parameter-error slope is approximately \(-\gamma I_*\) or more negative, and identification should continue after inputs are set to zero if one nonzero sample was stored. Sweep \(a_{\min}\) and predict hidden-state sensitivity decay no slower than \(e^{-a_{\min}t}\); allowing estimates to cross zero should create a sharp long-horizon instability boundary. Under noise, expect convergence to a residual floor rather than zero, with larger \(I_*\) reducing that floor.

## Verification

- Status: mech_ok_no_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: no_effect
- Verdict: Built and ran a readable concurrent-learning leak estimator with replay, projection, math sweeps, sensitivity checks, and a noisy-transition toy comparison. Predicted semilog error slopes matched -gamma I* within 0.08% across five replay sets, and epsilon-identification times matched the logarithmic prediction within 0.12%. Replay continued identifying the leak after the current state was zero, reducing error from 1.199 to 0.022 versus no reduction for current-only learning; the noisy demo also favored concurrent learning over fixed and current-only leaks.

### Mechanism check

- Verdict: Built and ran a readable concurrent-learning leak estimator with replay, projection, math sweeps, sensitivity checks, and a noisy-transition toy comparison. Predicted semilog error slopes matched -gamma I* within 0.08% across five replay sets, and epsilon-identification times matched the logarithmic prediction within 0.12%. Replay continued identifying the leak after the current state was zero, reducing error from 1.199 to 0.022 versus no reduction for current-only learning; the noisy demo also favored concurrent learning over fixed and current-only leaks.
- Confidence: 9/10
- Limitations: This is a one-dimensional toy transition experiment, not a trained copy/add task or multidimensional SSM. The noisy demo uses a simple fixed transition-noise setting and does not benchmark wall-clock speed, FLOPs, learned B, derivative-estimation filters, or realistic replay-buffer selection under substantial noise.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 1
- Paired wins: 0/8
- Benchmark verdict: no measurable effect

## Artifacts

- [bench_report.json](https://synthcore.org/code/726/bench_report.json)
- [bench_stage2.py](https://synthcore.org/code/726/bench_stage2.py)
- [report.md](https://synthcore.org/code/726/report.md)
- [report_bench_2026-09-01T012833.md](https://synthcore.org/code/726/report_bench_2026-09-01T012833.md)
- [results.json](https://synthcore.org/code/726/results.json)
- [verify.py](https://synthcore.org/code/726/verify.py)
- [Download all files as ZIP](https://synthcore.org/download/726)

## Disclaimer

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