This commit is contained in:
2026-01-27 18:39:24 +08:00
parent c46c25d607
commit a24c60c506
22 changed files with 357 additions and 8 deletions

View File

@@ -39,3 +39,12 @@
- **Why**: Avoid blind reweighting and find the specific features causing KS to stay high.
- **Files**:
- `example/diagnose_ks.py`
## 2026-01-26 — Quantile transform + sigmoid bounds for continuous features
- **Decision**: Add optional quantile normalization (TabDDPM-style) and sigmoid-based bounds to reduce KS spikes.
- **Why**: KS failures are dominated by boundary pile-up and tail mismatch.
- **Files**:
- `example/data_utils.py`
- `example/prepare_data.py`
- `example/export_samples.py`
- `example/config.json`