# Characteristic-Invariant BT Monitor

- ID: 2553
- Canonical URL: https://synthcore.org/idea/2553/characteristic-invariant-bt-monitor
- API JSON: https://synthcore.org/api/idea/2553.json
- API Markdown: https://synthcore.org/api/idea/2553.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.19018](https://arxiv.org/abs/2608.19018)
- Category: dynamics
- Solves: stability, accuracy
- ML areas: rnn, ssm, training-dynamics, regularization
- Math tags: dynamical-systems, bifurcations, linear-algebra, spectral-theory
- Ratings: usefulness 7/10; difficulty 5/10; novelty 8/10

## Idea description

Add a local bifurcation monitor to a neural ODE, continuous-time RNN, or state-space model by computing the central determinant and central trace from characteristic invariants of the state Jacobian. Their directional derivatives along the zero-eigenvalue direction estimate the BT coefficients and predict whether the model is approaching a codimension-two transition, allowing training to avoid destructive criticality or intentionally preserve a useful long-memory regime.

## Mathematical statement

Let the neural vector field be $\dot z=f_\theta(z,x)$ with equilibrium $f_\theta(z_*,x_*)=0$ and Jacobian $J=D_zf_\theta(z_*,x_*)\in\mathbb{R}^{n\times n}$. Define $e_k(J)$ as the sum of all principal $k\times k$ minors, so that $\det(\lambda I-J)=\sum_{k=0}^n(-1)^ke_k(J)\lambda^{n-k}$. At a BT point, $J$ has a zero eigenvalue of algebraic multiplicity two, rank $n-1$, and an invertible transverse block, represented by $e_{n-2}(J)\neq0$. For a nonzero $q_0\in\ker J$, define $D_{q_0}e_k=\nabla_z[e_k(D_zf_\theta(z,x_*))]_{z=z_*}^{\mathsf T}q_0$. The BT coefficients are $a=-\frac12D_{q_0}e_n/e_{n-2}$ and $b=D_{q_0}e_{n-1}/e_{n-2}-e_{n-3}D_{q_0}e_n/e_{n-2}^2$. Equivalently, $\delta=e_n/e_{n-2}$ and $\tau=(e_{n-1}e_{n-2}-e_ne_{n-3})/e_{n-2}^2$ satisfy $a=-\frac12D_{q_0}\delta$ and $b=D_{q_0}\tau$.

## Key formulas

- $$\det(\lambda I-J)=\sum_{k=0}^{n}(-1)^k e_k(J)\lambda^{n-k},\qquad e_k(J)=\sum_{|I|=k}\det J_{I,I}.$$
- $$\delta(J)=\frac{e_n(J)}{e_{n-2}(J)},\qquad \tau(J)=\frac{e_{n-1}(J)e_{n-2}(J)-e_n(J)e_{n-3}(J)}{e_{n-2}(J)^2}.$$
- $$a=-\frac{1}{2}\frac{D_{q_0}e_n}{e_{n-2}}=-\frac12D_{q_0}\delta,\qquad b=\frac{D_{q_0}e_{n-1}}{e_{n-2}}-\frac{e_{n-3}D_{q_0}e_n}{e_{n-2}^2}=D_{q_0}\tau.$$
- $$\text{BT candidate: }\delta(z_*)=0,\ \tau(z_*)=0,\ e_{n-2}(J)\neq0;\qquad\text{nondegenerate if }ab\neq0.$$

## Implementation notes

Use a continuous-time RNN or neural ODE with hidden state $z\in\mathbb{R}^n$ and dynamics $\dot z=f_\theta(z,x)$. At validation checkpoints, find an equilibrium $z_*$ by integrating with fixed input or solving $f_\theta(z_*,x)=0$ with Newton iterations. Compute $J=D_zf_\theta(z_*,x)$ using automatic differentiation. Obtain characteristic-polynomial coefficients and hence $e_k(J)$; for small models, direct principal-minor computation is acceptable, while larger models can use traces or polynomial algorithms. Estimate $q_0$ as the smallest right singular vector of $J$, normalize it, and use JVPs to compute directional derivatives of $e_k(D_zf_\theta(z,x))$ at $z_*$. Then evaluate $\delta$, $\tau$, $a$, and $b$. Add $L_{BT}=\rho_\delta\delta^2+\rho_\tau\tau^2$ when targeting criticality, or a barrier $L_{safe}=\rho/(e_{n-2}^2+\epsilon)$ when avoiding singular transverse blocks. The paper supplies the invariant formulas; equilibrium locations, null vectors, and derivatives are estimated numerically. First test a two- or four-dimensional tanh continuous-time RNN on damped-oscillator sequences, comparing unconstrained training with the monitor. Sweep a recurrent gain. The predicted signature is simultaneous zero crossing of measured $\delta$ and $\tau$ at the BT candidate, with trajectory fits recovering $\dot u_1\approx u_2$ and $\dot u_2\approx au_1^2+bu_1u_2$ within roughly 20 percent.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: inconclusive
- Verdict: Built a readable 2D continuous-time BT monitor with characteristic invariants, differentiable directional derivatives, finite-difference validation, and a baseline comparison. The three toy predictions manifested exactly: over 81 unfolding points delta=-mu and tau=nu with maximum error 0, and across four coefficient settings autodiff recovered a=alpha and b=beta with zero error; the candidate grid isolated delta=tau=0 at (mu,nu)=(0,0). The monitor optimization reached invariant loss 1.09e-12 versus 2.03 for the spectral-abscissa baseline, although this is a deliberately simple canonical system rather than evidence of a neural-network training win.

### Mechanism check

- Verdict: Built a readable 2D continuous-time BT monitor with characteristic invariants, differentiable directional derivatives, finite-difference validation, and a baseline comparison. The three toy predictions manifested exactly: over 81 unfolding points delta=-mu and tau=nu with maximum error 0, and across four coefficient settings autodiff recovered a=alpha and b=beta with zero error; the candidate grid isolated delta=tau=0 at (mu,nu)=(0,0). The monitor optimization reached invariant loss 1.09e-12 versus 2.03 for the spectral-abscissa baseline, although this is a deliberately simple canonical system rather than evidence of a neural-network training win.
- Confidence: 8/10
- Limitations: Only a 2D analytic canonical BT family was tested; no learned neural ODE or continuous-time RNN, equilibrium solver, noisy Jacobian estimation, higher-dimensional principal-minor implementation, trajectory-fit validation, GPU path, or runtime/FLOP comparison was evaluated. The n=2 transverse invariant is trivially e0=1, so transverse-block conditioning was not meaningfully stressed.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.1825
- Paired wins: 6/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_report.json](https://synthcore.org/code/980/bench_report.json)
- [bt_bench.py](https://synthcore.org/code/980/bt_bench.py)
- [bt_monitor_experiment.py](https://synthcore.org/code/980/bt_monitor_experiment.py)
- [report.md](https://synthcore.org/code/980/report.md)
- [report_bench_2026-09-01T172317.md](https://synthcore.org/code/980/report_bench_2026-09-01T172317.md)
- [results.json](https://synthcore.org/code/980/results.json)
- [Download all files as ZIP](https://synthcore.org/download/980)

## Disclaimer

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