Conformal risk control for bounded non-monotone losses over a grid of size m achieves excess risk of order sqrt(log m / n) with n calibration samples, which is minimax optimal.
Achieving risk control in online learning settings.arXiv preprint arXiv:2205.09095
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Conformal Risk Control under Non-Monotone Losses: Theory and Finite-Sample Guarantees
Conformal risk control for bounded non-monotone losses over a grid of size m achieves excess risk of order sqrt(log m / n) with n calibration samples, which is minimax optimal.