Presents the first online Learning-to-Defer algorithm achieving regret O((n + n_e) T^{2/3}) generally and O((n + n_e) sqrt(T)) under low noise for multiclass classification with varying experts.
Bartlett and Marten H
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ML 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Online Learning-to-Defer with Varying Experts
Presents the first online Learning-to-Defer algorithm achieving regret O((n + n_e) T^{2/3}) generally and O((n + n_e) sqrt(T)) under low noise for multiclass classification with varying experts.
-
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.