Эксперимент: Focus-Coefficient Switched Optimizer (#429)

{ "worked": true, "confidence": 8, "verdict": "Built a readable MVP implementing a radial normal-form switched dynamical system, RK4 integration, coefficient fitting, branch selection, and reproducible sweeps. The predicted c1 sign boundary was measured at -3.29e-6 versus the predicted 0, with maximum c1 fitting error 3.29e-6; the c2-leading sweep recovered c2 with maximum error 9.64e-4, and Delta-r/r^3 stayed within 0.7999996–0.7999999 across radii for true c1=0.8. Held-out branch selection chose the contracting branch in 90% of trials, meeting the stated 20% failure threshold, so the mathematical mechanism manifested in the toy system.", "metrics": { "baseline": "Fixed outward branch final radius 0.20348; fixed inward branch final radius 0.16313", "idea": "Coefficient-switched controller final radius 0.16649 from 0.18; held-out contracting-branch selection accuracy 90%; c1 boundary error 3.29e-6; c2 maximum estimation error 9.64e-4" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 focus_optimizer_mvp.py", "files": [ "focus_optimizer_mvp.py", "results.json", "run_output.txt" ], "limitations": "This verifies the focus-coefficient mechanism in a controlled two-dimensional toy vector field rather than a neural-network optimizer or MNIST MLP. It does not test real projected parameter/momentum trajectories, bootstrap confidence intervals, hysteresis, cosine scheduling, FLOPs, wall-clock speed, or GPU behavior; the fixed and switched comparison uses analytically specified branches rather than learned neural updates." }