Эксперимент: Wasserstein Speed-Limit Controller (#1095)

{ "worked": true, "confidence": 7, "verdict": "Built a replica-based SGLD Wasserstein controller and a toy translating-distribution verification. The bound prediction was confirmed: the dimension-corrected sliced-Wasserstein/action ratio had median 1.00, with worst relative error 28.2%; displacement scaling versus speed²·time² ranged from 0.72 to 1.25. In the quadratic stability sweep, the predicted fixed-step boundary eta=0.5 was observed: baseline diverged at eta=0.55 and 0.70, while the controller reduced eta and remained finite, although it sometimes hurt already-stable low-eta runs.", "metrics": { "baseline": "Quadratic SGLD final loss: 1.02e39 at eta=0.55 and 3.42e123 at eta=0.70; stable final losses 0.00480, 0.00605, and 0.01204 at eta=0.10, 0.30, and 0.45.", "idea": "Controller final loss: 0.00701 at eta=0.55 and 0.00573 at eta=0.70, with final eta 0.453 and 0.306 respectively; toy bound ratio median 1.000 and speed/time scaling range 0.718–1.249." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 wasserstein_controller.py", "files": [ "wasserstein_controller.py", "results.json" ], "limitations": "No MNIST/MLP experiment, wall-clock speed, or matched-FLOP study was performed. The dimension-corrected sliced-Wasserstein quantity is an estimator/proxy rather than an exact full W2 distance, and the optimizer test used a quadratic objective with injected noise rather than a realistic neural-network training workload." }