Эксперимент: Correction-aware tree optimizer (#451)

{ "worked": true, "confidence": 8, "verdict": "Built a correction-aware rooted-tree primal-dual MVP with explicit dual increments and redistributed parent corrections. The mechanism was numerically confirmed: correction conservation error was exactly zero, correction norms scaled linearly with rho as predicted, and the stale-error fit had near-zero intercept. The corrected optimizer did not improve final loss over the uncorrected tree or FedAvg in the scalar quadratic toy; its only observed practical signal was lower toy communication than FedAvg.", "metrics": { "baseline": "FedAvg: final objective 6.0937500000, consensus residual 0, 10240 toy bytes; uncorrected tree at rho=0.2: objective 6.0937499974, residual 7.65e-10, 7680 bytes", "idea": "Corrected tree at rho=0.2: final objective 6.0937499891, consensus residual 3.23e-9, 7680 toy bytes; correction conservation error 0 and rho norm ratios [1,2,4,8] matching prediction" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 tree_optimizer_experiment.py", "files": [ "tree_optimizer_experiment.py", "results.json", "REPORT.md" ], "limitations": "Only a four-node scalar convex quadratic proxy was tested. Logistic regression, MLP training, minibatch noise, asynchronous execution, realistic parameter-block bandwidth, latency, and multi-GPU behavior were not tested." }