A decoupled surrogate separates class posterior estimation from per-expert utility estimation, yielding a J-independent H-consistency bound and avoiding the amplification, starvation, and coupling issues of prior augmented-action surrogates.
When more experts hurt: Underfitting in multi-expert learning to defer
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
-
Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer
A decoupled surrogate separates class posterior estimation from per-expert utility estimation, yielding a J-independent H-consistency bound and avoiding the amplification, starvation, and coupling issues of prior augmented-action surrogates.