Эксперимент: Sensitivity-Conditioned Neural ODE Pruning (#881)

{ "worked": true, "confidence": 8, "verdict": "Built a compact neural-ODE unit-pruning experiment with weighted Fisher traces and leave-one-group sensitivity residuals, plus reproducible numerical verification. The mechanism checks passed: observed exponents were 2.000 for both information and residual amplitude scaling, -2.000 for noise scaling, and the collinearity residual matched C·sin(angle)^2 with ratio CV 1.0e-15. At 8/16 retained units, sensitivity pruning reached MSE 1.27e-6 and terminal error 0.00221 versus magnitude pruning MSE 2.31e-6 and terminal error 0.00297, but random pruning was better at MSE 3.94e-7 and terminal error 0.00131; therefore the mathematical mechanism manifested, but a practical accuracy win over random pruning was not demonstrated.", "metrics": { "baseline": "Magnitude: 24 parameters, MSE 2.305e-6, terminal error 0.002974; random: 24 parameters, MSE 3.943e-7, terminal error 0.001313", "idea": "Sensitivity: 24 parameters, MSE 1.266e-6, terminal error 0.002210; information/residual/noise observed scaling exponents 2.000/2.000/-2.000; angle-law ratio CV 1.05e-15" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 sensitivity_pruning_experiment.py", "files": [ "sensitivity_pruning_experiment.py", "results.json" ], "limitations": "Only a scalar damped nonlinear ODE and one 50% retention budget were tested; the requested 25% and 10% budgets, Lotka-Volterra trajectories, validation stopping, solver function-evaluation speed, Fisher condition numbers, and multiple random seeds were not evaluated. The sensitivity estimate uses finite differences through a fixed-step RK4 integrator rather than an augmented continuous adjoint sensitivity solve." }