In multi-distribution learning, the minimax-optimal predictor is calibrated only for the worst-case distribution, creating calibration disparities across other distributions.
Generalizing from several related classification tasks to a new unlabeled sample
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On Calibration in Multi-Distribution Learning
In multi-distribution learning, the minimax-optimal predictor is calibrated only for the worst-case distribution, creating calibration disparities across other distributions.