Principled approaches for learning to defer with multiple experts
We present a study of surrogate losses and algorithms for the general problem of learning to
defer with multiple experts. We first introduce a new family of surrogate losses specifically …
defer with multiple experts. We first introduce a new family of surrogate losses specifically …
Learning to Defer to a Population: A Meta-Learning Approach
The learning to defer (L2D) framework allows autonomous systems to be safe and robust by
allocating difficult decisions to a human expert. All existing work on L2D assumes that each …
allocating difficult decisions to a human expert. All existing work on L2D assumes that each …
Mitigating Underfitting in Learning to Defer with Consistent Losses
Learning to defer (L2D) allows the classifier to defer its prediction to an expert for safer
predictions, by balancing the system's accuracy and extra costs incurred by consulting the …
predictions, by balancing the system's accuracy and extra costs incurred by consulting the …
Enhanced -Consistency Bounds
Recent research has introduced a key notion of $ H $-consistency bounds for surrogate
losses. These bounds offer finite-sample guarantees, quantifying the relationship between …
losses. These bounds offer finite-sample guarantees, quantifying the relationship between …
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
Learn-to-Defer is a paradigm that enables learning algorithms to work not in isolation but as
a team with human experts. In this paradigm, we permit the system to defer a subset of its …
a team with human experts. In this paradigm, we permit the system to defer a subset of its …
Realizable -Consistent and Bayes-Consistent Loss Functions for Learning to Defer
We present a comprehensive study of surrogate loss functions for learning to defer. We
introduce a broad family of surrogate losses, parameterized by a non-increasing function …
introduce a broad family of surrogate losses, parameterized by a non-increasing function …
Learning to Complement and to Defer to Multiple Users
With the development of Human-AI Collaboration in Classification (HAI-CC), integrating
users and AI predictions becomes challenging due to the complex decision-making process …
users and AI predictions becomes challenging due to the complex decision-making process …
A Causal Framework for Evaluating Deferring Systems
Deferring systems extend supervised Machine Learning (ML) models with the possibility to
defer predictions to human experts. However, evaluating the impact of a deferring strategy …
defer predictions to human experts. However, evaluating the impact of a deferring strategy …
Two-stage Learning-to-Defer for Multi-Task Learning
The Learning-to-Defer approach has been explored for classification and, more recently,
regression tasks separately. Many contemporary learning tasks, however, involves both …
regression tasks separately. Many contemporary learning tasks, however, involves both …
Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
Learning-to-Defer (L2D) facilitates optimal task allocation between AI systems and decision-
makers. Despite its potential, we show that current two-stage L2D frameworks are highly …
makers. Despite its potential, we show that current two-stage L2D frameworks are highly …