Volterra BBP multi-timescale recurrent initialization
Implementation & benchmark of arXiv:2607.10503 — A Cascade of Volterra-Operator BBP Transitions in a Correlated Wigner Matrix
Source paper: A Cascade of Volterra-Operator BBP Transitions in a Correlated Wigner Matrix arXiv:2607.10503 ⓘ · analyzed Aug 30, 2026
AI-generated research hypothesis, automatically tested. Not peer-reviewed.
Idea description
Initialize a recurrent or state-space transition matrix with weak Wigner noise plus a shared cumulative-sum correlation structure. Increasing the correlation strength produces recurrent eigenmodes one at a time at analytically predicted BBP thresholds, yielding a controllable hierarchy of short- and long-memory modes. The matrix should then be globally rescaled or constrained so that all active modes remain inside the desired stability radius.
Formulas
Mathematical statement
Let $G$ be a symmetric Wigner matrix with independent centered unit-variance entries, let $Z_1,\ldots,Z_N$ be independent centered unit-variance factors, and define the symmetric shared-factor matrix $M_{ij}=Z_{\max(i,j)}$ for $i\neq j$ and $M_{ii}=Z_i$. Construct $W_0=(\sigma/\sqrt{N})G+(b/N)M$, where $\sigma>0$ is the bulk-noise scale and $b\geq 0$ is the correlation strength. In the continuum limit, the correlated eigenvalues are governed by the singular values $s_k$ of the Volterra operator $(Vf)(t)=\int_0^t f(u)\,du$ on $[0,1]$, with $s_k=1/((k-1/2)\pi)$. Equivalently, the eigenvalues of $V^*V$ are $s_k^2=1/((k-1/2)^2\pi^2)$. The $k$th BBP transition occurs approximately when $b s_k=\sigma$, and above threshold the associated outlier is approximately $\lambda_k=b s_k+\sigma^2/(b s_k)$, outside the Wigner bulk edge $2\sigma$. For a recurrent update $h_{t+1}=\phi(Wh_t+Ux_t)$, a global gain can enforce a target spectral radius below one while preserving the relative outlier hierarchy.
Implementation notes
First, integrate the construction at the recurrent transition matrix of a tanh RNN, a linear state-space model, or a recurrent world model. Sample a symmetric Wigner matrix $G$ and a vector $Z$ of independent standard normal variables. Form $M[i,j]=Z[\max(i,j)]$, symmetrize it, and set $W_0=\sigma G/\sqrt{N}+bM/N$. Estimate the largest eigenvalue using 10 to 30 power iterations, then rescale with $g=r/(|\lambda_{\max}(W_0)|+10^{-6})$, where $r$ is typically 0.9 or 0.95. The forward update is $h=\tanh(gW_0h+Ux)$. Optionally make $b$ trainable and add the penalty $\alpha\max(0,\rho(W)-r)^2$, estimating $\rho(W)$ by power iteration. The paper supplies the Volterra singular values and predicted thresholds $b_{c,k}=\sigma/s_k$; the implementation estimates finite-size eigenvalues, actual nonlinear Jacobian growth, and task performance. Run a cheap experiment with $N=256$ tanh RNNs on copy-memory and adding tasks, comparing this initialization against iid Gaussian and orthogonal initialization with matched optimizer settings. For $\sigma=0.5$, sweep $b$ across the first several predicted thresholds and diagonalize $W_0$. The falsifiable prediction is a staircase: the number of eigenvalues outside the bulk edge $2\sigma$ should increase near $b_{c,k}=\sigma/s_k$, with the first few transition locations within about 20 percent at finite $N$. Perturbations projected onto each outlier eigenvector should decay approximately as $|g\lambda_k|^t$, producing distinct memory timescales.
Verification
Stage 1 · Toy mechanism gate: Failed ✗
Stage 2 · Mechanism transferred to benchmark: Not tested
Stage 2 · Practical benchmark result: Not run
Methodology: Toy-system gate first; the benchmark stage runs only after a pass. How verification works
Stage 1 — Mechanism check agent confidence 9/10
Built and tested the Volterra BBP initialization, including matrix construction, spectral staircase sweeps, outlier asymptotic checks, global gain rescaling, and an independent Volterra discretization. The analytic Volterra singular values matched to 0.10%, and rescaling produced the requested spectral radius 0.900 versus 0.9. However, the finite-size first transition occurred at b=0.609 versus predicted 0.785 (22.5% relative error), while the outlier formula errors were 1.4% for mode 1 but 127% and 282% for modes 2 and 3; therefore the claimed multi-timescale BBP mechanism was not confirmed.
- Agent confidence
- 9/10
- Baseline
- For comparison-only spectral-radius checks at N=96, iid Gaussian mean rho=0.516 and orthogonal mean rho=0.500; no task-accuracy win was established.
- Idea
- Volterra singular-value relative error <=0.101%; gain-rescaled rho=0.899999 versus target 0.900; first transition b=0.609 observed versus 0.785 predicted; outlier-formula mean relative errors k=1: 1.4%, k=2: 127.3%, k=3: 282.4%.
- Thresholds
- Predicted b thresholds for sigma=0.5: [0.785, 2.356, 3.927, 5.498].
Limitations: The planned tanh copy-memory/adding-task comparison was not run after the spectral mechanism failed; experiments used a reduced N=96 and 8 or fewer repeats because the original N=256 sweep exceeded the execution budget. The implemented M is the stated random max-index factor matrix, but its finite-dimensional spectral structure was not theoretically re-derived beyond the supplied claim.
How to run: python3 volterra_bbp_experiment.py && /home/maxwelhelp/main/bin/python3 verify_volterra.py
Verdict computed by deterministic test code from paired-seed statistics — not by the language model.
Artifacts
- report.md 1.9 KB View
- results.json 3.6 KB View Raw
- verify_volterra.py 0.6 KB View Raw
- volterra_bbp_experiment.py 4.2 KB View Raw
- volterra_singular_values.json 0.5 KB View Raw