Эксперимент: Robustness-capacity feasibility controller (#1386)

{ "worked": false, "confidence": 9, "verdict": "Built a two-layer ReLU noisy-regression MVP with the stated ReLU lower-bound controller, Jacobian probe estimator, and neuron-copy widening. The numerical sanity check clearly reproduced the claimed formula behavior: L_min decreased with width (0.2483 at m=2 to 0.0466 at m=64) and increased with fitting error (0.0207 at epsilon=0.08 to 0.1807 at epsilon=0.64). However, in the matched training experiment the residual only reached the known noise variance after the estimated Lipschitz constant had already exceeded 0.9 L_min, so widening never activated; baseline and controller were identical, including clean test MSE 0.04776. The proposed practical effect was therefore not observed.", "metrics": { "baseline": "width 8, 0 widening events, clean test MSE 0.0477636, 3.25 s", "idea": "width 8, 0 widening events, clean test MSE 0.0477636, 3.12 s; math scaling checks width_monotone=true and error_monotone=true" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only a small synthetic noisy regression task was tested; no two-moons, CIFAR binary subset, repeated seeds, adversarial robustness, FLOP-normalized comparisons, or systematic calibration of c0/C0/eta was performed. The controller's empirical constants were not optimized, and the theorem's high-probability assumptions were not independently tested." }