Principled approaches for learning to defer with multiple experts

A Mao, M Mohri, Y Zhong - International Workshop on Combinatorial …, 2024 - Springer
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 …

Learning to Defer to a Population: A Meta-Learning Approach

D Tailor, A Patra, R Verma… - International …, 2024 - proceedings.mlr.press
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 …

Mitigating Underfitting in Learning to Defer with Consistent Losses

S Liu, Y Cao, Q Zhang, L Feng… - … Conference on Artificial …, 2024 - proceedings.mlr.press
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 …

Enhanced -Consistency Bounds

A Mao, M Mohri, Y Zhong - arxiv preprint arxiv:2407.13722, 2024 - arxiv.org
Recent research has introduced a key notion of $ H $-consistency bounds for surrogate
losses. These bounds offer finite-sample guarantees, quantifying the relationship between …

A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems

MA Charusaie, S Samadi - arxiv preprint arxiv:2407.12710, 2024 - arxiv.org
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 …

Realizable -Consistent and Bayes-Consistent Loss Functions for Learning to Defer

A Mao, M Mohri, Y Zhong - arxiv preprint arxiv:2407.13732, 2024 - arxiv.org
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 …

Learning to Complement and to Defer to Multiple Users

Z Zhang, W Ai, K Wells, D Rosewarne, TT Do… - … on Computer Vision, 2024 - Springer
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 …

A Causal Framework for Evaluating Deferring Systems

F Palomba, A Pugnana, JM Alvarez… - arxiv preprint arxiv …, 2024 - arxiv.org
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 …

Two-stage Learning-to-Defer for Multi-Task Learning

Y Montreuil, SH Yeo, A Carlier, LX Ng… - arxiv preprint arxiv …, 2024 - arxiv.org
The Learning-to-Defer approach has been explored for classification and, more recently,
regression tasks separately. Many contemporary learning tasks, however, involves both …

Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees

Y Montreuil, A Carlier, LX Ng, WT Ooi - arxiv preprint arxiv:2502.01027, 2025 - arxiv.org
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 …