Saved in:
Bibliografiske detaljer
Main Authors: Huang, Jiayi, Park, Sangwoo, Paoletti, Nicola, Simeone, Osvaldo
Format: Preprint
Udgivet: 2025
Fag:
Online adgang:https://arxiv.org/abs/2510.17543
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!
_version_ 1866917038580039680
author Huang, Jiayi
Park, Sangwoo
Paoletti, Nicola
Simeone, Osvaldo
author_facet Huang, Jiayi
Park, Sangwoo
Paoletti, Nicola
Simeone, Osvaldo
contents Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging. We study edge-cloud cascades that must preserve conditional coverage: whenever the edge returns a prediction set, it should contain the true label with a user-specified probability, as if produced by the cloud model. We formalize conditional coverage with respect to the cloud predictive distribution, and introduce a conformal alignment-based (CAb) cascading mechanism that certifies this property with user control over the risk level. Our method casts escalation from edge to cloud models as a multiple-hypothesis testing (MHT) problem, tailoring conformal alignment (CA) to select which inputs can be safely handled at the edge. The proposed CAb model cascading method yields statistical guarantees on the average fraction of edge decisions that satisfy cloud-level conditional coverage. The procedure applies to arbitrary edge prediction sets, including variants of conformal prediction (CP), and exposes a tunable trade-off among coverage, deferral rate, and set size. Experiments on CIFAR-100 image classification and the TeleQnA question-answering (QA) benchmark show that the proposed CAb cascade maintains the target conditional coverage for edge predictions while substantially reducing offloading to the cloud and incurring modest increases in prediction-set size.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17543
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment
Huang, Jiayi
Park, Sangwoo
Paoletti, Nicola
Simeone, Osvaldo
Machine Learning
Signal Processing
Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging. We study edge-cloud cascades that must preserve conditional coverage: whenever the edge returns a prediction set, it should contain the true label with a user-specified probability, as if produced by the cloud model. We formalize conditional coverage with respect to the cloud predictive distribution, and introduce a conformal alignment-based (CAb) cascading mechanism that certifies this property with user control over the risk level. Our method casts escalation from edge to cloud models as a multiple-hypothesis testing (MHT) problem, tailoring conformal alignment (CA) to select which inputs can be safely handled at the edge. The proposed CAb model cascading method yields statistical guarantees on the average fraction of edge decisions that satisfy cloud-level conditional coverage. The procedure applies to arbitrary edge prediction sets, including variants of conformal prediction (CP), and exposes a tunable trade-off among coverage, deferral rate, and set size. Experiments on CIFAR-100 image classification and the TeleQnA question-answering (QA) benchmark show that the proposed CAb cascade maintains the target conditional coverage for edge predictions while substantially reducing offloading to the cloud and incurring modest increases in prediction-set size.
title Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2510.17543