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 …
Multi-label learning with stronger consistency guarantees
We present a detailed study of surrogate losses and algorithms for multi-label learning,
supported by $ H $-consistency bounds. We first show that, for the simplest form of multi …
supported by $ H $-consistency bounds. We first show that, for the simplest form of multi …
A universal growth rate for learning with smooth surrogate losses
This paper presents a comprehensive analysis of the growth rate of $ H $-consistency
bounds (and excess error bounds) for various surrogate losses used in classification. We …
bounds (and excess error bounds) for various surrogate losses used in classification. We …
Cardinality-Aware Set Prediction and Top- Classification
We present a detailed study of cardinality-aware top-$ k $ classification, a novel approach
that aims to learn an accurate top-$ k $ set predictor while maintaining a low cardinality. We …
that aims to learn an accurate top-$ k $ set predictor while maintaining a low cardinality. We …
-Consistency Guarantees for Regression
We present a detailed study of $ H $-consistency bounds for regression. We first present
new theorems that generalize the tools previously given to establish $ H $-consistency …
new theorems that generalize the tools previously given to establish $ H $-consistency …
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 …
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 Partially Defer for Sequences
S Rayan, A Tewari - arxiv preprint arxiv:2502.01459, 2025 - arxiv.org
In the Learning to Defer (L2D) framework, a prediction model can either make a prediction or
defer it to an expert, as determined by a rejector. Current L2D methods train the rejector to …
defer it to an expert, as determined by a rejector. Current L2D methods train the rejector to …
Learning to Help in Multi-Class Settings
Deploying complex machine learning models on resource-constrained devices is
challenging due to limited computational power, memory, and model retrainability. To …
challenging due to limited computational power, memory, and model retrainability. To …
Domain Adaptation for Robust Model Routing
The rapid proliferation of domain-specialized machine learning models presents a
challenge: while individual models excel in specific domains, their performance varies …
challenge: while individual models excel in specific domains, their performance varies …