mlsanityData to 7 Oct 2026

Learning To Help: Training Models to Assist Legacy Devices

arXiv 2409.16253 ↗First posted 24 Sep 2024cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Machine learning models implemented in hardware on physical devices may be deployed for a long time. The computational abilities of the device may be limited and become outdated with respect to newer improvements. Because of the size of ML models, offloading some computation (e.g. to an edge cloud) can help such legacy devices. We cast this problem in the framework of learning with abstention (LWA) in which the expert (edge) must be trained to assist the client (device). Prior work on LWA trains the client assuming the edge is either an oracle or a human expert. In this work, we formalize the reverse problem of training the expert for a fixed (legacy) client. As in LWA, the client uses a rejection rule to decide when to offload inference to the expert (at a cost). We find the Bayes-optimal rule, prove a generalization bound, and find a consistent surrogate loss function. Empirical results show that our framework outperforms confidence-based rejection rules.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 24 Sep 2024.

Builds on

14 of 25 references.

References · 14

  1. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  2. 2020Consistent Estimators for Learning to Defer to an Expertcited by 262
  3. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 228
  4. 2018To Trust Or Not To Trust A Classifiercited by 205
  5. 2021Machine Learning with a Reject Option: A surveycited by 107
  6. 2019The Algorithmic Automation Problem: Prediction, Triage, and Human Effortcited by 101
  7. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  8. 2022Calibrated Learning to Defer with One-vs-All Classifierscited by 68
  9. 2023Who Should Predict? Exact Algorithms For Learning to Defer to Humanscited by 68
  10. 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 59
  11. 2021Teaching Humans When To Defer to a Classifier via Exemplarscited by 29
  12. 2023In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defercited by 26
2 more
  1. 2023Learning to Defer with Limited Expert Predictionscited by 25
  2. 2019Does deep learning always outperform simple linear regression in optical imaging?cited by 4

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Learning to Help in Multi-Class Settingscited by 2
  2. 2025From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascadescited by 1