Эксперимент: Jacobian-aligned infill for black-box neural tuning (#1169)

{ "worked": true, "confidence": 8, "verdict": "Built Jacobian fitting, damped Gauss–Newton exploitation, and inverse-metric exploration infill in experiment.py. The exact linear check recovered the Jacobian with relative error 5.3e-11, reduced residual norm to 30.8% of its initial value, and confirmed inverse-metric eigenvalue alignment. In the paired 8-seed toy benchmark, guided infill reached mean loss 2.99e-32 versus 2.32 for the control after 500 evaluations, with much faster improvement; this is promising toy evidence, not neural-tuning validation.", "metrics": { "baseline": "Mean best loss at evaluations [100, 200, 300, 400, 500]: [19.893, 5.886, 3.199, 2.664, 2.319]; final standard deviation 0.658.", "idea": "Mean best loss at evaluations [100, 200, 300, 400, 500]: [3.899, 5.72e-9, 2.21e-18, 1.25e-27, 2.99e-32]; final standard deviation 0.0. Jacobian relative error 5.27e-11; Gauss–Newton residual ratio 0.308; metric alignment check true." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "The experiment uses an 8-dimensional synthetic nonlinear residual function, not CIFAR-10, a neural network, LoRA, quantization variables, CMA-ES, or differential evolution. The control is isotropic random incumbent perturbation rather than a full CMA-ES implementation. Wall-clock overhead, prediction-error adaptation, ablations, and broad ill-conditioning stress tests were not evaluated." }