Эксперимент: Removable-Pole Negative-Shifted Optimizer (#511)

{ "worked": true, "confidence": 9, "verdict": "Built a readable spectral NS-GD MVP and an anisotropic quadratic-regression comparison in experiment.py. The removable-pole limit matched f(nu)=nu*t exactly, off-pole error scaled linearly, mixed-sign crossover roots agreed with dense sweeps within 2.2e-5, and the Euler stability boundary matched eta=2/(s-nu) within 2.6e-4. The regression run did not show an accuracy win: NS-GD test MSE was 0.6523 versus 0.5875 for GD and 0.5859 for positive ridge, with 2.04x the GD parameter norm.", "metrics": { "baseline": "GD: test MSE 0.5875058, train MSE 0.4680532, parameter norm 0.3604186; positive ridge: test MSE 0.5859458", "idea": "NS-GD: test MSE 0.6522977, train MSE 0.3875421, parameter norm 0.7347119; removable-pole error 0, near-pole slope 0.999997, crossover error <=2.2e-5, Euler-boundary error 2.6e-4" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only a deterministic full-batch linear regression toy was tested; no CIFAR-10, neural-network or LoRA block, minibatch noise, validation-based nu/K selection, Hessian-vector estimation, clipping, or wall-clock/FLOP comparison was run." }