Эксперимент: Alignment-Section Floquet Training for Recurrent Dynamics (#1166)

{ "worked": true, "confidence": 7, "verdict": "Built a compact PyTorch MVP with a planar rotating limit cycle, return-residual training, autodiff monodromy, and a non-neutral Floquet penalty. The analytic check showed geometric perturbation contraction across successive periods. In training, the baseline had Floquet radius 1.0066 and event error grew to 0.1083, while the idea had radius 0.00077 and event error stabilized near 0.0161, providing a promising stability signal. The result may also indicate over-contraction, so it is not conclusive evidence of improved modeling quality.", "metrics": { "baseline": "Floquet rho=1.0066; return MSE=4.29e-05; final 15-period event error=0.1083", "idea": "Floquet rho=0.00077; return MSE=1.287e-04; final 15-period event error=0.01608; analytic perturbation ratios=0.1637, 0.0267, 0.00406, 0.000787" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only one seed and one small planar system were tested. The implementation uses a fixed-period return instead of sign-change event interpolation, does not explicitly project neutral section directions, and does not test larger RNNs, learned symmetries, multiple seeds, or FLOP-normalized comparisons." }