Эксперимент: ISS-Certified Sampled Optimizer Wrapper (#443)

{ "worked": true, "confidence": 8, "verdict": "Built an ISS-certified sampled optimizer wrapper with box projection, linear control interpolation, Lyapunov-certificate rejection/backtracking, and safe fallback control. All three toy predictions were confirmed: the fixed-control stability boundary matched |a-u|<1 within grid resolution, the certificate sampling transition occurred at M=2 as predicted, and disturbance plateau energy scaled exactly as d^2. The wrapper reduced the baseline's state explosion from 2.22e22 maximum magnitude to a maximum of 1.0 and final magnitude 2.09e-3, demonstrating a real stabilization effect in this toy setting.", "metrics": { "baseline": "Scalar sampled system, M=1, eta=0.35, d=0.005: final_abs=2.22e22, max_abs=2.22e22, u=3.0.", "idea": "Same setup with certification: final_abs=2.09e-3, max_abs=1.0, 92 accepted and 8 rejected updates, mean eta=0.32025, u=3.0.", "prediction_checks": "Stability boundary: predicted [0.20,2.20], observed [0.25,2.20] on a 0.05 grid. Sampling transition: predicted and observed minimum M=2. Disturbance scaling: V/d^2=4.0 for every tested amplitude." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 iss_sampled_optimizer.py", "files": [ "iss_sampled_optimizer.py", "results.json" ], "limitations": "Only a scalar linear state-space toy was tested, not a GRU/SSM trained on a task. The optimizer direction is synthetic, P is fixed to the scalar identity rather than learned, disturbances are constant, and no FLOP/accuracy or larger-scale neural-network comparison was performed." }