# Symmetry-Resolved Fourier Bifurcation Monitor

- ID: 2109
- Canonical URL: https://synthcore.org/idea/2109/symmetry-resolved-fourier-bifurcation-monitor
- API JSON: https://synthcore.org/api/idea/2109.json
- API Markdown: https://synthcore.org/api/idea/2109.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.11101](https://arxiv.org/abs/2608.11101)
- Category: dynamics
- Solves: stability, accuracy
- ML areas: rnn, ssm, optimizer, training-dynamics
- Math tags: dynamical-systems, bifurcations, control-theory, harmonic-analysis, linear-algebra
- Ratings: usefulness 7/10; difficulty 6/10; novelty 7/10

## Idea description

Decompose a periodic recurrent or state-space model into group-symmetry sectors and temporal Fourier modes, then monitor the restricted characteristic spectrum instead of only the full Jacobian. Use the first sector whose characteristic value approaches zero or whose winding number changes to reduce the learning rate, increase damping, or deliberately activate a new dynamical mode.

## Mathematical statement

Let G be a finite symmetry group acting on hidden states through a representation ρ(g), and let Mθ be the linearized one-period return map of the neural dynamical system at parameters θ. Decompose the hidden space into isotypical components Vσ indexed by irreducible representations σ of G, and periodic perturbations into temporal Fourier modes k. Let Jσ,k be the restriction of the linearized operator to the (σ,k) block and define the characteristic function χσ,k(μ) = det(μI − Jσ,k). A local bifurcation candidate occurs when χσ,k(1) = 0 for a discrete-time return map. For a complex symbol, a winding number wσ,k = (1/(2πi))∮Γ d log χσ,k(μ) detects robust zero crossings. In the neural adaptation, the blockwise spectral margin mσ,k = |1 − λmax(Jσ,k)| is used as a measurable stability signal; λmax denotes the eigenvalue closest to one in the relevant block.

## Key formulas

- hₜ₊₁ = Fθ(hₜ,xₜ),   Mθ = ∂hₜ₊₁/∂h₀ = Πₜ₌₀ᵀ⁻¹ ∂Fθ/∂hₜ
- H = ⊕σ ⊕k Hσ,k,   χσ,k(μ) = det(μI − Jσ,k)
- mσ,k = |1 − λσ,k|,   candidate bifurcation when mσ,k ≤ ε
- wσ,k = (1/(2πi)) ∮Γ [∂μχσ,k(μ)/χσ,k(μ)] dμ

## Implementation notes

1. Integration point: use this monitor in a periodic RNN, linear state-space model, or recurrent memory module with rollout length T. Require a finite group action on hidden channels, such as cyclic channel permutations or a dihedral reflection-plus-rotation action. Precompute the representation projectors Pσ for each symmetry sector. 2. Pseudocode: periodically run a no-gradient rollout; estimate Jacobian-vector products for the one-period map Mθ; project vectors with Pσ; apply a temporal FFT to obtain approximate blocks Jσ,k; use power iteration or Arnoldi to estimate the eigenvalue λσ,k closest to one; compute mσ,k. If the minimum margin falls below ε, multiply the optimizer step by min(1,mmin/m0), or add damping −γPσh only to the critical sector. Optionally evaluate χσ,k on a small complex circle and unwrap its phase to estimate the winding number. 3. Computed from the paper's mechanism: symmetry decomposition, Fourier decomposition, restricted characteristic functions, and winding-style crossing indicators. Estimated empirically: Jacobian blocks, eigenvalues, truncation error, and the practical threshold ε. 4. First cheap experiment: train a cyclic-equivariant GRU on length-64 trajectories from a noisy Kuramoto ring. Compare global spectral clipping with blockwise monitoring over a grid of recurrent gain and learning rate. The prediction is that divergence begins when the first block eigenvalue reaches the unit circle, so the measured divergence boundary should agree with mσ,k = 0 within 20 percent. The critical spatial sector should also predict the Fourier pattern that dominates unstable rollouts.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: inconclusive
- Verdict: Built an exact cyclic-equivariant Fourier-sector monitor with restricted eigenvalue margins, characteristic-circle winding checks, temporal FFT utilities, and a reproducible toy sweep. All four mechanism predictions manifested: the unit-circle boundary was 1.075 versus predicted 1.0753 (0.025% error), the margin slope was -0.930 versus -0.930, and the predicted critical sector and winding transitions were recovered exactly. In the small optimization comparison, blockwise damping reached final loss 0.000181 versus 0.001430 for global damping, although this is a controlled linear toy rather than a trained GRU or Kuramoto task.

### Mechanism check

- Verdict: Built an exact cyclic-equivariant Fourier-sector monitor with restricted eigenvalue margins, characteristic-circle winding checks, temporal FFT utilities, and a reproducible toy sweep. All four mechanism predictions manifested: the unit-circle boundary was 1.075 versus predicted 1.0753 (0.025% error), the margin slope was -0.930 versus -0.930, and the predicted critical sector and winding transitions were recovered exactly. In the small optimization comparison, blockwise damping reached final loss 0.000181 versus 0.001430 for global damping, although this is a controlled linear toy rather than a trained GRU or Kuramoto task.
- Confidence: 9/10
- Limitations: The experiment uses an exactly known linear circulant return map, not a learned GRU, noisy Kuramoto trajectories, or estimated Jacobian-vector products. Temporal Fourier extraction is implemented as a utility but was not used in the optimization comparison, and no GPU or wall-clock benchmark was needed.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.78655
- Paired wins: 4/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_report.json](https://synthcore.org/code/852/bench_report.json)
- [bench_stage2.py](https://synthcore.org/code/852/bench_stage2.py)
- [report.md](https://synthcore.org/code/852/report.md)
- [report_bench_2026-09-01T124921.md](https://synthcore.org/code/852/report_bench_2026-09-01T124921.md)
- [results.json](https://synthcore.org/code/852/results.json)
- [symmetry_monitor.py](https://synthcore.org/code/852/symmetry_monitor.py)
- [Download all files as ZIP](https://synthcore.org/download/852)

## Disclaimer

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