# Эксперимент: Trusted Polytopic Optimizer Steps (#1049)

{
  "worked": true,
  "confidence": 8,
  "verdict": "Built a two-coordinate trusted-polytopic optimizer MVP with nonlinear rollout prediction, box refinement using vertices and face midpoints, and quadratic-model candidate selection. The toy mechanism matched all three quantitative predictions: local violation slope 2.006 versus 2, trust radius versus tolerance slope 0.490 versus 0.5, and monotone increasing horizon error. In the tiny MLP test, the trusted method reached loss 0.1065 versus SGD 0.1266 after 40 updates, but required 4040 versus 40 gradient evaluations, so no speedup claim is supported.",
  "metrics": {
    "baseline": "SGD: final/best loss 0.1266002150, 40 gradient evaluations",
    "idea": "Trusted 2D polytope: final/best loss 0.1064823206, mean radius 0.09536, 4040 gradient evaluations; toy slopes 2.0056 and 0.4896 versus predictions 2.0 and 0.5"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 trusted_polytope.py",
  "files": [
    "trusted_polytope.py",
    "results.json",
    "run.txt"
  ],
  "limitations": "The neural experiment is a tiny synthetic 2D binary classification task implemented in NumPy, not MNIST/CIFAR or a full Adam integration. The trust set is an approximate sampled box rather than a certified polytope, curvature is estimated directionally, and computational cost was not equalized beyond reporting gradient-evaluation counts; no multi-seed or large-scale benchmark was run."
}