Эксперимент: Cap-free golden-ratio primal-dual optimizer (#1392)

{ "worked": false, "confidence": 8, "verdict": "Built a cap-free golden-ratio primal-dual optimizer with elastic-net proximal regularization, box-constraint dual updates via Moreau's identity, local curvature adaptation, and controls for proximal gradient, projected proximal gradient, and AdamW. The math sanity check passed: the finite-difference curvature estimate matched the analytic Hessian action with 0.10% relative error, and the golden-ratio coefficients summed to one. GRPD maintained the explicit constraint at all tested initial steps and reached loss 0.07735 versus 0.10555 for projected PG at step 0.02, but the claimed fewer-divergence/larger-step stability win was not demonstrated because every method remained finite across the tested sweep; therefore worked=false.", "metrics": { "baseline": "Projected PG final losses: 0.10555, 0.08904, 0.08438, 0.07971, 0.07702, 0.07685, 0.07685 for initial steps 0.02, 0.05, 0.1, 0.2, 0.5, 1.0, 2.0; constraint violation was zero throughout.", "idea": "GRPD final losses: 0.07735, 0.07735, 0.07732, 0.07729, 0.07725, 0.07730, 0.07752 at the same steps; violations were zero except approximately 0.00035 at steps 0.5 and 1.0. Curvature relative error was 0.000975." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json", "run.log", "run2.log" ], "limitations": "Only a small full-batch convex logistic problem and one fixed random seed were tested. No neural network, minibatch noise, CIFAR/features, multiple independent runs, GPU execution, runtime/FLOP comparison, or genuinely divergent regime was evaluated; the convex paper guarantee was not tested beyond this toy setting." }