Эксперимент: Convex-gradient robust augmenter (#701)

{ "worked": true, "confidence": 9, "verdict": "Built an exact quadratic convex-gradient transport prototype and a two-moons comparison. The mechanism checks confirmed the predicted identity minimum, quadratic near-identity KL scaling, and linear dimension scaling; the Monte Carlo change-of-variables KL estimate matched the analytic value within 0.72%. The classifier result was not a clear practical win: ConvexTransport matched ERM on shifted accuracy but reduced clean accuracy.", "metrics": { "baseline": "ERM: clean accuracy 0.9633, shifted accuracy 0.9633, clean log loss 0.0775; Gaussian: clean accuracy 0.9700, shifted accuracy 0.9600", "idea": "ConvexTransport: clean accuracy 0.9533, shifted accuracy 0.9633, clean log loss 0.1099; prescribed KL radius rho=0.06137", "math_checks": "Identity KL minimum: exact zero at scale 1.0; quadratic KL ratio mean 0.99388 versus prediction 1.0; dimension slope 0.0376784 observed versus predicted 0.0376784; change-of-variables KL relative error 0.72%" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py", "files": [ "convex_transport.py", "run_experiment.py", "results.json" ], "limitations": "Only a quadratic isotropic/diagonal transport family and one small two-moons experiment were tested. Learned class-conditional ICNN/HyCNN potentials, Sinkhorn optimization, adversarial ascent, KDE estimation, PGD and unconstrained augmenter baselines, multiple seeds, image data, and learned-radius sweeps were not tested." }