EFundAI / label-horizon-paradoxView on GitHub
[ICML'26] An open-source demo of the bi-level optimization (BLO) method from "The Label Horizon Paradox". Reproduces the core method (BLO + brute-force baseline + backtest) on public Alpha158 factors and A-share data, showing that the optimal training label horizon can deviate from the inference target.
☆16Aug 26, 2026Updated 2 months ago

Alternatives and similar repositories for label-horizon-paradox

Users that are interested in label-horizon-paradox are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?