Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles.
Rajeev VermaDaniel BarrejónEric T. NalisnickPublished in: AISTATS (2023)
Keyphrases
- learning algorithm
- reinforcement learning
- learning tasks
- learning systems
- learning process
- human experts
- multiple tasks
- combining multiple
- inductive inference
- learning scheme
- camera calibration
- knowledge acquisition
- online learning
- supervised learning
- decision trees
- unsupervised learning
- focal length
- mobile devices
- neural network