Эксперимент: Conditional Sinkhorn Adversarial Augmentation (#538)

{ "worked": true, "confidence": 8, "verdict": "Built a differentiable conditional-generator wrapper using a residual adversarial shift, debiased entropic Sinkhorn divergence, radius penalty, projected multiplier ascent, and outer predictor descent. The mechanism checks succeeded: S(delta) fit k*delta^2 with k=0.9858 and maximum relative error 0.276%, the rho=0.36 boundary was predicted at delta=0.6043 and observed at 0.6 (error 0.0043), S(A,A)=0, and lambda stayed zero below rho while increasing after violations. The tiny downstream regression comparison did not produce a win: Sinkhorn training retained clean MSE 0.1893 but had shifted MSE 0.4956 versus ordinary 0.4768; unconstrained augmentation traded clean MSE 0.4538 for shifted MSE 0.1956. Thus worked=true reflects confirmed mathematical mechanism, not an observed application-level improvement.", "metrics": { "baseline": "ordinary: clean MSE 0.1882, shifted MSE 0.4768", "idea": "conditional Sinkhorn: clean MSE 0.1893, shifted MSE 0.4956, final S 0.2552 versus rho 0.16, lambda 0.8381; math scaling fit k=0.9858, max relative error=0.00276, radius-boundary absolute error=0.00431" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "This is a one-dimensional synthetic conditional-regression toy, not a CIFAR, trajectory, GAN, or diffusion experiment. The adversarial generator is only a scalar residual adapter, the Sinkhorn implementation uses small uniform empirical samples and fixed iterations, there is one seed, and the final multiplier still permits a modest radius violation; no FLOP or wall-clock comparison was performed." }