Эксперимент: Integral Sparse Dynamics Training (#827)

{ "worked": true, "confidence": 7, "verdict": "The MVP confirmed the predicted derivative-noise amplification: integral increment variance stayed near 0.0098 while finite-difference variance followed 0.0098 divided by delta-t squared. Support recovery degraded when the active Gram minimum eigenvalue approached zero. The integral method achieved a small clean-increment MSE improvement, but not a decisive win.", "metrics": { "baseline": "clean increment MSE 2.6686e-5; support F1 1.00", "idea": "clean increment MSE 2.5573e-5; support F1 1.00; at rho=0.99, active Gram minimum eigenvalue 0.00664 and support F1 0.50" }, "how_to_run": "python3 integral_sparse_dynamics.py", "files": [ "integral_sparse_dynamics.py", "integral_sparse_dynamics_v1.py", "results.json" ], "limitations": "The test used a linear toy sparse-regression system rather than a tanh RNN or neural ODE. It did not test Adam, minibatching, higher-order quadrature, repeated seeds, confidence intervals, or runtime. The support-recovery trend was qualitative and non-monotonic at intermediate correlations." }