# Эксперимент: Van der Corput progressive expert scheduler (#634)

{
  "worked": true,
  "confidence": 9,
  "verdict": "Built a readable binary van der Corput scheduler and numerical verification experiment in files vdc_moe_experiment.py and results.json. Across D=2..64, endpoint error at n=D was exactly 0, maximum nested discrepancy was 0.5..0.984 (always below the stated B(D)=1.33..3.0), and VDC leaf prefix error stayed below 1. In the synthetic capacity test with D=8 and 128 assignments, VDC had zero drops and zero load variance at capacity factor 1.0, versus 9.3% drops for random routing and 61.0% for greedy routing; this demonstrates the scheduling mechanism, not end-to-end model accuracy.",
  "metrics": {
    "baseline": "Random routing: at D=8, mean final leaf imbalance 3.275 and mean max nested-prefix discrepancy 4.484; capacity factor 1.0 averaged 9.30% drops and load variance 4.16. Greedy routing: 60.98% drops and load variance 17.94 at capacity factor 1.0.",
    "idea": "VDC: at D=8, max leaf/nested prefix discrepancy 0.875, endpoint error at n=D exactly 0, and capacity factor 1.0 averaged 0% drops and 0 load variance. Across D=2..64, max nested discrepancy remained below B(D) and max leaf error remained below 1."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 vdc_moe_experiment.py",
  "files": [
    "vdc_moe_experiment.py",
    "results.json",
    "run_output.txt"
  ],
  "limitations": "The experiment is a scheduler/capacity simulation rather than a trained Switch-Transformer or CIFAR/language-model benchmark. It does not test router-logit integration, learned expert specialization, FLOPs, validation loss, classification accuracy, perplexity, GPU behavior, or the midpoint interval-discrepancy claim; the random baseline uses a reduced trial count for runtime."
}