# Эксперимент: Wavelet Conditional Sampler for Neural EBMs (#1129)

{
  "worked": true,
  "confidence": 7,
  "verdict": "Built a self-contained 2-D orthogonal Haar hierarchical conditional sampler and numerically verified the proposed mechanism in its synthetic Gaussian model. Reconstruction and Parseval errors were below 5e-16; conditional residual standard deviation stayed at the predicted sigma across L=8–64, scaled linearly with sigma, was insensitive to rho, and the transition count fit transitions=1.0000*log2(L)+0.0000. The ancestral wavelet sampler had integrated autocorrelation near 1 versus 46–116 for the tested pixel-space ULA, but this is only a toy exact conditional model, not evidence for a learned neural EBM.",
  "metrics": {
    "baseline": "Pixel-space Gaussian ULA mean-observable IAT: L=8 46.10, L=16 115.87, L=32 58.63",
    "idea": "Wavelet ancestral mean-observable IAT: L=8 1.040, L=16 1.003, L=32 1.154; conditional residual std for sigma=0.35 across L=8,16,32,64: 0.3502, 0.3485, 0.3501, 0.3500; log-scale transition fit slope=1.0000, intercept=0.0000; sigma sweep observed stds 0.1500, 0.3497, 0.7003"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 wavelet_sampler_experiment.py",
  "files": [
    "wavelet_sampler_experiment.py"
  ],
  "limitations": "No learned conditional networks, neural energy model, Ising/quartic Gibbs target, finite-step conditional Langevin correction, likelihood, FID, structure-factor, wall-clock, FLOP, or GPU experiment was tested. The baseline uses an estimated Gaussian precision and the wavelet sampler is exact by construction, so the comparison is illustrative rather than a fair end-to-end EBM benchmark."
}