Эксперимент: Inverse-Square Adaptive Parameter Reset (#1088)

{ "worked": false, "confidence": 9, "verdict": "Built an inverse-square stochastic reset diffusion simulator, parameter sweeps, lambda controls, and a small SGD checkpoint-reset wrapper in experiment.py. The algebraic beta formula and critical ratio r0/D=2 are internally consistent, but measured tail exponents stayed near 4 across the sweep and did not track predicted beta values; the lambda classification was also not observed. The optimizer appeared better in one confounded sine-regression test, but this is not evidence for the proposed mechanism because it used online best-validation checkpoint restoration and an arbitrary hazard scale.", "metrics": { "baseline": "SGD validation MSE 6.2002 on the small noisy sine-regression stress test", "idea": "Inverse-square checkpoint-reset wrapper validation MSE 0.5158 with 353 resets; toy fitted density exponents approximately 3.90-4.70 for predicted beta values 0.366-2.372, with no confirmed transition near r0/D=2" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json", "REPORT.txt" ], "limitations": "The diffusion experiment used shortened trajectories and a finite reflecting box after the initial timeout, so asymptotic tail estimation was noisy and finite-time effects may matter. No MNIST experiment, rigorous stationary-distribution solver, fair multi-seed optimizer benchmark, or empirical estimation of D from minibatch parameter increments was performed." }