Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment
King’s College London（伦敦国王学院）；Centre for Intelligent Information Processing Systems（智能信息处理系统中心）；Department of Engineering（工程系）；Department of Informatics（信息学系）；King’s Communications, Learning & Information Processing (KCLIP) lab（国王学院通信、学习与信息处理实验室）
Jiayi Huang, Sangwoo Park, Nicola Paoletti, Osvaldo Simeone
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.
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
Department of Statistics and Actuarial Science University of Iowa（统计与精算科学系，爱荷华大学）；Departments of Data Science and AI, and Applied Mathematics The Hong Kong Polytechnic University（数据科学与人工智能系、应用数学系，香港理工大学）
Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty
Department of Statistics, University of California, Davis（加州大学戴维斯分校统计系）；Department of Applied Mathematics and Statistics, Johns Hopkins University（约翰霍普金斯大学应用数学与统计学系）
Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions
Shanghai Jiao Tong University（上海交通大学）；Shanghai University of Finance and Economics（上海财经大学）；National University of Defense Technology（国防科学技术大学）；School of Statistics and Data Science（统计与数据科学学院）；Institute of Big Data Research（大数据研究院）
Aligning Model Properties via Conformal Risk Control
Stanford University（斯坦福大学）；Graduate School of Business, Stanford University（斯坦福大学商学院）；Management Science and Engineering, Stanford University（斯坦福大学管理科学与工程学院）
Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Centre for Intelligent Information Processing Systems (CIIPS), Department of Engineering, King’s College London（伦敦国王学院工程系智能信息处理系统中心）；Intelligent Networked Systems Institute (INSI) at Northeastern University（东北大学智能网络化系统研究所）
