# Эксперимент: Flow-Efficiency Drift Scheduler (#1337)

{
  "worked": true,
  "confidence": 7,
  "verdict": "Built a reproducible 16-D eight-mode mixture experiment with ESS, symmetric-KL drift estimation, adaptive FIFO window/update scheduling, local correction, and importance-evidence diagnostics. The math checks passed: ESS stayed in range and was invariant to log-weight shifts; symmetric KL was positive and approximately symmetric within Monte Carlo noise. Adaptation improved mean ESS from 0.1445 to 0.1791, reduced ESS<0.02 levels from 21 to 15, and reduced mean log-evidence error from 5.42 to 0.98, but it did not maintain the promised eta>=0.1 floor and used 148 versus 28 flow updates plus 120 correction steps, so this is a promising signal rather than a demonstrated efficient win.",
  "metrics": {
    "baseline": "mean eta=0.1445; min eta=0.000880; 21/28 levels eta<0.1; 21/28 eta<0.02; mean absolute log-evidence error=5.4232; total R=28",
    "idea": "mean eta=0.1791; min eta=0.000878; 18/28 levels eta<0.1; 15/28 eta<0.02; mean absolute log-evidence error=0.9774; total R=148; local correction steps=120"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 scheduler_experiment.py",
  "files": [
    "scheduler_experiment.py",
    "results.json"
  ],
  "limitations": "This is a toy mixture-center simulator, not a learned neural flow or true HMC/Langevin implementation. The local correction uses access to the current target center as an oracle-like proxy, thresholds were hand-selected, only one fixed seed/run was used, and no wall-clock or FLOP-normalized comparison was measured."
}