Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Yau's affine-normal descent enables scalable unrestricted higher-moment portfolio optimization by working directly with the return matrix and exploiting quartic structure for exact oracles and line searches.
citing papers explorer
-
Risk-Controlled Post-Processing of Decision Policies
Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
-
Yau's Affine-Normal Descent for Large-Scale Unrestricted Higher-Moment Portfolio Optimization
Yau's affine-normal descent enables scalable unrestricted higher-moment portfolio optimization by working directly with the return matrix and exploiting quartic structure for exact oracles and line searches.