Online Conformal Probabilistic Numerics via Adaptive Edge-Cloud Offloading

2025-03-18

AI Summary

In edge computing, time-varying computational resources cause the uncertainty sets produced by probabilistic linear solvers (PLS) to degrade over time, failing to reliably cover the true solution. Method: This paper proposes OCP-PLS—a novel framework that integrates online conformal prediction (OCP) into probabilistic numerical computation for the first time, enabling model-free, online calibration of uncertainty sets; it synergistically combines edge-side PLS with sparse cloud feedback to support adaptive recalibration under dynamic computational budgets. Contributions/Results: Experiments demonstrate that OCP-PLS consistently achieves the target 95% coverage guarantee, while significantly reducing uncertainty set size, decreasing cloud invocation frequency, and jointly optimizing statistical reliability, real-time responsiveness, and communication efficiency.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Planning, Routing, and Scheduling: Planning under Uncertainty

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Consider an edge computing setting in which a user submits queries for the solution of a linear system to an edge processor, which is subject to time-varying computing availability. The edge processor applies a probabilistic linear solver (PLS) so as to be able to respond to the user's query within the allotted time and computing budget. Feedback to the user is in the form of an uncertainty set. Due to model misspecification, the uncertainty set obtained via a direct application of PLS does not come with coverage guarantees with respect to the true solution of the linear system. This work introduces a new method to calibrate the uncertainty sets produced by PLS with the aim of guaranteeing long-term coverage requirements. The proposed method, referred to as online conformal prediction-PLS (OCP-PLS), assumes sporadic feedback from cloud to edge. This enables the online calibration of uncertainty thresholds via online conformal prediction (OCP), an online optimization method previously studied in the context of prediction models. The validity of OCP-PLS is verified via experiments that bring insights into trade-offs between coverage, prediction set size, and cloud usage.

Problem

• Calibrates uncertainty sets for probabilistic linear solvers
• Ensures long-term coverage guarantees for linear system solutions
• Adapts thresholds using online conformal prediction with cloud feedback

Innovation

• Online conformal prediction for uncertainty calibration
• Adaptive edge-cloud offloading for sporadic feedback
• Probabilistic linear solver with coverage guarantees