# Эксперимент: DMDc-Initialized Marginal-Stable Neural SSM (#254)

{
  "worked": false,
  "confidence": 9,
  "verdict": "Built a compact DMDc-initialized residual latent model with Hankel delay lifting, ridge DMDc fitting, eigenvalue inspection, and a random-transition recurrent baseline. The numerical checks confirmed exact noiseless recovery, ridge error scaling linearly with regularization (log-log slope 0.9999), and bounded projected dynamics, but the forecasting experiment showed no win: DMDc had higher validation, horizon-10, and horizon-50 MSE than the random baseline.",
  "metrics": {
    "baseline": "initial/train checkpoint losses [0.3198, 0.3164, 0.0310]; validation MSE 0.03560; horizon-10 MSE 0.01083; horizon-50 MSE 0.05698; final spectral radius 1.0090",
    "idea": "initial/train checkpoint losses [1.2308, 0.3204, 0.0416]; validation MSE 0.05639; horizon-10 MSE 0.01916; horizon-50 MSE 0.07392; DMDc spectral radius 1.01325"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py",
  "files": [
    "experiment.py",
    "results.json"
  ],
  "limitations": "Only a small synthetic scalar nonlinear forecasting task was tested; no electricity or battery benchmark, FLOP-matched parameter audit, gradient-variance analysis, multiple-seed study, or implemented post-update spectral projection was evaluated. The DMDc backbone was frozen in this experiment, and its noisy estimate was slightly unstable, which may disadvantage the idea."
}