Эксперимент: Task-Visible Axis Pruning (#1396)

{ "worked": true, "confidence": 7, "verdict": "Built a reproducible ReLU MLP pruning MVP with magnitude, activation-mean, and task-visible-axis criteria. The core structural claim was numerically verified: explicitly positive/negative axes were correctly classified by quantiles, and absorbing them into adjacent affine computation produced maximum error 1.8e-15. On digits, task-visible pruning gave a small accuracy advantage after fine-tuning at 75% and 25% retained width, but not at 50%, so the practical win is promising but not consistent.", "metrics": { "baseline": "Unpruned accuracy 0.9711; validation loss 0.1298.", "idea": "Task-visible accuracy after 3 fine-tuning epochs: 0.9756 at 75% width, 0.9600 at 50%, and 0.9022 at 25%; corresponding magnitude-pruning results were 0.9689, 0.9622, and 0.8956. Exact one-sided-axis absorption error was 1.8e-15." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py", "files": [ "run_experiment.py", "results.json" ], "limitations": "Only one fixed-seed digits split and one small MLP were tested. Masks were applied as structured zeroing rather than physically rebuilding compact layers, so parameter/FLOP and wall-clock speedups were not measured. The m_l(epsilon) stopping-rule search, multiple calibration patches/seeds, and CNN/real CIFAR-10 evaluation were not tested." }