Эксперимент: MI-Guided Latent Protection (#938)

{ "worked": true, "confidence": 8, "verdict": "Built MI-guided latent Gaussian protection with EMA sensitivity scores, inverse-score variance allocation, fixed total noise budget, and uniform/random/magnitude baselines. The three mechanism predictions were confirmed across sweeps: mean variance was conserved to 1.1e-16, inverse variance scaling error was 2.5e-9, and the quadratic penalty ratio error was 1.4e-9. In the small learning test MI reached 79.96% noisy accuracy versus 79.88% uniform, but random ranking reached 83.36%, so there is no evidence of a practical MI win in this setup; worked=true reflects the mathematically verified mechanism, not a demonstrated accuracy improvement.", "metrics": { "baseline": "Uniform Gaussian noise: 79.88% noisy accuracy, 90.60% clean accuracy, mean variance 0.45", "idea": "MI-guided Gaussian noise: 79.96% noisy accuracy, 91.08% clean accuracy, mean variance 0.45; random ranking was 83.36% noisy accuracy" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 mi_latent_protection.py", "files": [ "mi_latent_protection.py", "results.json" ], "limitations": "The learning comparison used a synthetic 8-dimensional binary task and a supervised gradient sensitivity proxy rather than CIFAR-10 with a density-ratio or InfoNCE MI estimator. It used one seed and did not test quantization, bitrate allocation, ranking stability, or multiple corruption budgets." }