# Steady-State First-Passage Sensitivity Regularizer

- ID: 2117
- Canonical URL: https://synthcore.org/idea/2117/steady-state-first-passage-sensitivity-regularizer
- API JSON: https://synthcore.org/api/idea/2117.json
- API Markdown: https://synthcore.org/api/idea/2117.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.11202](https://arxiv.org/abs/2608.11202)
- Category: dynamics
- Solves: stability, accuracy, speedup
- ML areas: rnn, ssm, diffusion-sampling, training-dynamics
- Math tags: stochastic-processes, probability, statistics, dynamical-systems, control-theory
- Ratings: usefulness 7/10; difficulty 6/10; novelty 8/10

## Idea description

Treat a neural hidden-state process as a finite or discretized continuous-time Markov chain and define a target event as first entry into a target state set. Instead of estimating the derivative of the mean hitting time by expensive long rollouts, build an auxiliary regenerative chain that resets to the source state after reaching the target and estimate the same response from its stationary distribution. Penalize disagreement between this response prediction and short empirical perturbation measurements, or directly optimize the perturbation direction that decreases target hitting time.

## Mathematical statement

Let $X_t$ be a continuous-time Markov chain with generator $Q(\theta)$, where $\theta$ is a neural-network parameter or controllable perturbation, and let $T_{ij}(\theta)=\mathbb{E}_i[\tau_j]$ with $\tau_j=\inf\{t\geq0:X_t=j\}$. Construct an auxiliary regenerative chain by retaining the original transitions until the process reaches target $j$ and then resetting it to source $i$; let $\widetilde{\pi}^{ij}(\theta)$ be its stationary distribution and $\widetilde{Q}^{ij}(\theta)$ its generator. The renewal-reward identity makes $T_{ij}$ the mean regenerative cycle duration, while the paper's exact correspondence expresses derivatives of $T_{ij}$ with respect to $\theta$ through steady-state response quantities of the auxiliary chain. For a scalar perturbation $h$, use the linear response $R_{ij}=\left.\partial_hT_{ij}\right|_{h=0}$ and estimate it from the stationary derivative of the auxiliary chain instead of long first-passage trajectories. The construction assumes finite $T_{ij}$, an ergodic auxiliary chain, and differentiable transition rates.

## Key formulas

- $$T_{ij}(\theta)=\mathbb{E}_i[\tau_j]=\int_0^\infty \Pr_i(\tau_j>t)\,dt,$$
- $$\widetilde{Q}^{ij}_{ab}(\theta)=Q_{ab}(\theta)\quad(a\neq j),\qquad \widetilde{Q}^{ij}_{ia}(\theta)\leftarrow \widetilde{Q}^{ij}_{ia}(\theta)+Q_{ja}(\theta),$$
- $$\widetilde{\pi}^{ij}(\theta)\widetilde{Q}^{ij}(\theta)=0,\qquad \sum_a\widetilde{\pi}^{ij}_a(\theta)=1,$$
- $$R_{ij}=\left.\frac{\partial T_{ij}(h)}{\partial h}\right|_{h=0},\qquad \widehat{R}_{ij}^{\mathrm{FD}}=\frac{\widehat{T}_{ij}(+h)-\widehat{T}_{ij}(-h)}{2h},\qquad \mathcal{L}_{\mathrm{FPT}}=\left|\widehat{R}_{ij}^{\mathrm{aux}}-\widehat{R}_{ij}^{\mathrm{FD}}\right|^2$$

## Implementation notes

1. Integration point: use a recurrent neural network or neural state-space model with hidden state $z_t$. Choose a source region $A$ and target region $B$, such as the initial hidden-state cluster and the set of states classified as a correct terminal prediction. Discretize hidden states into $K$ clusters, or define a differentiable local transition generator $Q_\phi(\theta)$ with nonnegative off-diagonal rates generated by softplus functions. Let $h$ perturb input noise, temperature, a control gain, or a selected parameter direction. 2. Pseudocode: collect hidden-state trajectories; estimate $Q_{ab}=N_{ab}/D_a$, where $N_{ab}$ is the number of transitions from state $a$ to $b$ and $D_a$ is total dwell time in $a$; copy $Q$; redirect every transition entering target $B$ to source $A$ to form $\widetilde Q^{AB}$; solve $\widetilde\pi\widetilde Q=0$ with normalization by an augmented linear system; repeat for $+h$ and $-h$; differentiate or finite-difference the stationary quantity; add $\lambda\mathcal L_{\mathrm{FPT}}$ to the network loss. 3. Computed from the paper's mechanism: the regenerative auxiliary construction and the equality between first-passage response and auxiliary steady-state response. Estimated empirically: transition rates, state clustering, stationary distributions, and finite-sample derivatives. 4. First cheap experiment: train a small GRU on sequential MNIST or a two-state switching task, defining the target as correct classification for three consecutive steps. Compare vanilla training, direct first-passage-loss training, and this auxiliary-response regularizer. Measure MFPT for perturbations $h\in[-0.1,0.1]$ using 10,000 rollouts and compare centered finite differences with the auxiliary estimate. The quantitative prediction is linear-response agreement as $h\to0$, with relative error below 20% after each auxiliary state has at least 100 observed transitions. The MFPT curve should have slope $R_{ij}$. A failure boundary is also predicted: when the auxiliary chain loses ergodicity or $T_{ij}$ becomes very large, the stationary solve becomes ill-conditioned and the response variance should increase sharply.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: inconclusive
- Verdict: Built and numerically verified the regenerative fast-reset CTMC method in experiment.py. The exact paper response formula matched centered finite differences to 1.3e-10; auxiliary stationary-response error decreased from 11.8% at reset rate 2 to 0.031% at rate 1000, with observed log-log slope -0.996 versus the predicted -1 scaling. The nonlinear rational-response formula had maximum absolute error 0.050 across six finite perturbations, and the predicted symmetry/sign behavior was confirmed; the rollout baseline was much noisier.

### Mechanism check

- Verdict: Built and numerically verified the regenerative fast-reset CTMC method in experiment.py. The exact paper response formula matched centered finite differences to 1.3e-10; auxiliary stationary-response error decreased from 11.8% at reset rate 2 to 0.031% at rate 1000, with observed log-log slope -0.996 versus the predicted -1 scaling. The nonlinear rational-response formula had maximum absolute error 0.050 across six finite perturbations, and the predicted symmetry/sign behavior was confirmed; the rollout baseline was much noisier.
- Confidence: 9/10
- Limitations: This is an exact four-state CTMC toy verification, not a neural RNN training experiment. It does not test learned state clustering, auxiliary regularizer optimization, GPU behavior, very large MFPT or ill-conditioned regimes, or the claimed 100-transition empirical threshold.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.89505
- Paired wins: 4/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_fpt.py](https://synthcore.org/code/853/bench_fpt.py)
- [bench_report.json](https://synthcore.org/code/853/bench_report.json)
- [experiment.py](https://synthcore.org/code/853/experiment.py)
- [report.md](https://synthcore.org/code/853/report.md)
- [report_bench_2026-09-01T125928.md](https://synthcore.org/code/853/report_bench_2026-09-01T125928.md)
- [results.json](https://synthcore.org/code/853/results.json)
- [Download all files as ZIP](https://synthcore.org/download/853)

## Disclaimer

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