Эксперимент: Green-Margin Residual Dynamics (#917)

{ "worked": true, "confidence": 8, "verdict": "Built a Green-Margin residual MVP with discrete Green-kernel computation, stable/unstable diagonal channels, scalar fixed-point sweeps, and a matched 20-layer residual regression comparison. The mechanism manifested: q scaled linearly with slope 3.3333, the observed contraction boundary was eta=0.3159 versus predicted 0.3000 (5.3% error), and the response matched 1/(1-q) to 1.8e-15 relative error. Margin control reduced peak gradients from 8.06 to 0.330 and maintained effective q=0.8, but final MSE was worse, 0.261 versus 0.176, so this is a stability win rather than an accuracy win.", "metrics": { "baseline": "final MSE 0.17585; maximum parameter gradient 8.0576; effective q 5.1004", "idea": "final MSE 0.26123; maximum parameter gradient 0.3305; raw q 76.8434; effective q after rescaling 0.8000; residual scale 0.01041; toy q slope 3.3333 observed versus 3.3333 predicted; boundary eta 0.3159 observed versus 0.3000 predicted; response-law maximum relative error 1.8e-15" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py", "files": [ "run_experiment.py", "results.json", "run_output.txt", "REPORT.md" ], "limitations": "The training comparison is a tiny linear regression experiment rather than MNIST or CIFAR, uses conservative global residual rescaling instead of differentiable per-layer Jacobian penalties, and does not test learned nonautonomous or nonlinear backbones, generalization, FLOPs, or long-run training stability." }