Эксперимент: Adaptive CUR Neural Layer (#1308)

{ "worked": false, "confidence": 9, "verdict": "Built an adaptive CUR layer with truncated-SVD pseudoinverse, residual random-sketch leverage refresh, warm-start index retention, and factorized forward evaluation. The core identity was verified to numerical precision (maximum batch-output gap 2.3e-14), and a rank-8 matrix was recovered at about 1e-15 relative error with 2.74x parameter-count compression. However, after an out-of-index-set weight change, adaptive refresh had mean relative error 4.89 versus 0.864 for stale CUR and 1.52 for random CUR across 20 seeds, beating stale only once; the claimed adaptive tracking effect was not observed.", "metrics": { "baseline": "Dense reconstruction error 0; stale fixed CUR post-change mean relative error 0.864; random CUR post-change mean relative error 1.521; dense parameters 5120.", "idea": "Adaptive residual-leverage CUR post-change mean relative error 4.890, median 2.388, beating stale in 1/20 seeds; compressed factor count 1872 (2.74x fewer parameters); formula evaluation max absolute gap 2.33e-14." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 adaptive_cur.py && /home/maxwelhelp/main/bin/python3 sweep.py", "files": [ "adaptive_cur.py", "sweep.py" ], "limitations": "Only a small synthetic matrix experiment was tested; no CIFAR MLP, Transformer, optimizer fine-tuning, activation distillation, refresh-period training study, GPU benchmark, wall-clock latency, FLOP measurement, or condition-number mitigation was evaluated. The observed instability likely requires better sampling, rank/retention scheduling, or conditioning safeguards before neural-layer testing." }