Эксперимент: Histogram-Controlled Cluster Updates for Iterative GNNs (#467)

{ "worked": true, "confidence": 8, "verdict": "Built a readable toy implementation of histogram observations, quantization, synchronous cluster scattering, and a residual-driven cluster selector. Histogram permutation/cardinality invariance and quantizer thresholds matched exactly; the stale sequential-vs-synchronous error followed the predicted eta^2 law with maximum error 1.1e-16. The mini-comparison ended at residual 74 for both full synchronous and histogram-selected updates, so the mechanism is real but this experiment did not establish a practical speedup or lower residual.", "metrics": { "baseline": "Full synchronous updates: final residual 74 after 30 sweeps (2,880 node updates).", "idea": "Histogram-selected cluster updates: final residual 74 after 240 cluster decisions (2,880 node updates); 8x more sequential decisions than full sweeps, with no observed residual improvement." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "This is a small synthetic continuous-signal toy, not a trained recurrent GNN or Q-learning scheduler. It does not test METIS/BFS partitioning, GPU wall-clock utilization, learned policies, graph coloring/SAT accuracy, larger graphs, or statistical averages over multiple problem seeds." }