Decoupled surrogate for multi-expert L2D with independent heads produces an excess-risk calibration constant independent of expert pool size under fixed per-expert weight.
h -consistency bounds: Characterization and extensions
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
Decoupled surrogate for multi-expert L2D with independent heads produces an excess-risk calibration constant independent of expert pool size under fixed per-expert weight.