# Finite-Horizon Walk Reciprocity Control

- ID: 150
- Canonical URL: https://synthcore.org/idea/150/finite-horizon-walk-reciprocity-control
- API JSON: https://synthcore.org/api/idea/150.json
- API Markdown: https://synthcore.org/api/idea/150.md
- Verification status: mech_ok_no_baseline
- Source: [arXiv:2608.25030](https://arxiv.org/abs/2608.25030)
- Category: dynamics
- Solves: stability, generalization
- ML areas: training-dynamics, regularization, initialization, graph-nn
- Math tags: dynamical-systems, stochastic-processes, linear-algebra, graph-theory, spectral-theory
- Ratings: usefulness 6/10; difficulty 5/10; novelty 7/10

## Idea description

Add a diagnostic and optional regularizer that measures whether a neural block's multi-step directed interactions differ strongly when traversed forward versus backward. This catches transient directional amplification in deep acyclic or nearly nilpotent networks, which eigenvalue or spectral-radius penalties can miss because all eigenvalues may be zero even though short directed walks are large.

## Mathematical statement

The paper identifies antisymmetric directed-walk matrices as the source of irreversibility. For an interaction matrix \(A\in\mathbb{R}^{n\times n}\), the length-\(k\) aggregate walk matrix is \(W_k=A^k\), with \((W_k)_{ij}\) equal to the total signed weight of length-\(k\) directed walks from node \(j\) to node \(i\). Its nonreciprocal component is \(D_k=W_k-W_k^{\mathsf T}\), where \({\mathsf T}\) denotes transpose. Use the finite-horizon walk energy \(R_L(A,g)=\frac{1}{n}\sum_{k=1}^{L}g^{2k-2}\|D_k\|_F^2\), where \(L\) is the measured horizon, \(g\in[0,1)\) is a gain parameter, \(n\) is width, and \(\|\cdot\|_F\) is the Frobenius norm. The paper's reported universal reference curve is \(\phi_*(g)=1-\sqrt{1-g^2}\). A corresponding target walk budget can be defined as \(R_{\mathrm{target}}=c\,\phi_*(g)\), with dimensionless calibration constant \(c\) measured from a baseline. The key structural warning is that a nilpotent matrix satisfies \(A^d=0\) and has all eigenvalues equal to zero, while \(A^k\neq0\) for \(k<d\); therefore finite-horizon walk statistics detect transient interactions invisible to eigenvalue diagnostics.

## Key formulas

- $$\phi_*(g)=1-\sqrt{1-g^{2}},\qquad g\in[0,1)$$
- $$W_k=A^k,\qquad D_k=W_k-W_k^{\mathsf T}=(A^k)-(A^k)^{\mathsf T}$$
- $$R_L(A,g)=\frac{1}{n}\sum_{k=1}^{L}g^{2k-2}\left\|A^k-(A^k)^{\mathsf T}\right\|_F^2$$
- $$A^d=0\ \text{but}\ A^k\neq0\ (k<d),\qquad \operatorname{spec}(A)=\{0,\ldots,0\}$$

## Implementation notes

Integrate this into the training-dynamics instrumentation of a residual MLP, Transformer feed-forward block, or directed GNN. For a block with local linearized interaction matrix \(A\), use either the weight matrix itself after row/column normalization, or a Jacobian-vector proxy measured at the current minibatch. First normalize \(A\leftarrow A/(\|A\|_2+\epsilon)\), choose a small horizon \(L=4\) or \(8\), and choose \(g=0.8\). Compute the walk terms without explicitly materializing all dense powers when width is large: maintain \(V_k=A V_{k-1}\) and estimate \(\|V_k-V_k^{\mathsf T}\|_F^2\) with 8--32 Hutchinson vectors, or use exact powers for a small-width pilot. Pseudocode: `R=0; V=A; for k in 1..L: D=V-transpose(V); R += g**(2*k-2)*mean_square(D); V=A@V`. During the first experiment, log \(R_L\), gradient norm, activation norm, and validation loss; optionally add \(\lambda\max(0,R_L-R_{target})^2\) to the loss, where \(R_{target}=c\phi_*(g)\) and \(c\) is the median baseline ratio \(R_L/\phi_*(g)\) collected during the first epoch. The paper supplies the square-root reference law and the nilpotent/transient rationale; the normalization, finite horizon, Hutchinson estimator, and target coefficient are empirical engineering choices. Start with a 6-layer width-256 residual MLP on CIFAR-10 or a small directed node-classification GNN, comparing standard spectral-norm regularization, no regularizer, and this walk penalty at equal FLOPs. Success is lower activation/gradient spikes and improved validation accuracy or loss stability, especially in strictly feed-forward acyclic networks where spectral-radius measurements remain near zero.

## Verification

- Status: mech_ok_no_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: inconclusive
- Verdict: Built an exact finite-horizon reciprocity diagnostic, differentiable walk-energy regularizer, nilpotent sanity check, and three-seed toy regression comparison. A strictly triangular nilpotent matrix had spectral radius 0 and A^n=0, yet substantial positive finite-horizon walk energy (3.664), while a symmetric control had approximately zero energy; iterative powers matched exact powers to 1.1e-16. The regularizer reduced walk energy in all three seeds, but did not reliably improve loss and increased mean gradient norm, so a practical training win is not established.

### Mechanism check

- Verdict: Built an exact finite-horizon reciprocity diagnostic, differentiable walk-energy regularizer, nilpotent sanity check, and three-seed toy regression comparison. A strictly triangular nilpotent matrix had spectral radius 0 and A^n=0, yet substantial positive finite-horizon walk energy (3.664), while a symmetric control had approximately zero energy; iterative powers matched exact powers to 1.1e-16. The regularizer reduced walk energy in all three seeds, but did not reliably improve loss and increased mean gradient norm, so a practical training win is not established.
- Confidence: 8/10
- Limitations: Only a tiny synthetic full-batch regression task and three seeds were tested; no CIFAR-10, Transformer, GNN, spectral-norm baseline, Hutchinson estimator, validation split, FLOP-normalized comparison, or broad hyperparameter sweep was evaluated. The target was calibrated from each seed's baseline final-window energy rather than a separately measured first-epoch median.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.09615
- Paired wins: 6/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_report.json](https://synthcore.org/code/1189/bench_report.json)
- [bench_walk_reciprocity.py](https://synthcore.org/code/1189/bench_walk_reciprocity.py)
- [report.md](https://synthcore.org/code/1189/report.md)
- [report_bench_2026-09-03T030023.md](https://synthcore.org/code/1189/report_bench_2026-09-03T030023.md)
- [results.json](https://synthcore.org/code/1189/results.json)
- [walk_reciprocity_experiment.py](https://synthcore.org/code/1189/walk_reciprocity_experiment.py)
- [Download all files as ZIP](https://synthcore.org/download/1189)

## Disclaimer

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