---
title: "Robust Active Learning for More Efficient and Reliable Paths to Optimal Design"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.38582v1"
permalink: "https://feed.astralor.com/items/itm_d1e42b21e94fd356c8d2fc5d"
published: "2026-10-28T10:11:21.000Z"
score: 53
channel: "tech"
tags: ["Robust Active Learning","More Efficient","Reliable Paths","Optimal Design Simulation-driven","Multifidelity Cost-Aware Screening","MF-CA","Simulation-driven"]
---

# Robust Active Learning for More Efficient and Reliable Paths to Optimal Design

## 速览

Simulation-driven design optimization requires active learning strategies that efficiently combine models with different computational costs and levels of fidelity. We introduce Multifidelity Cost-Aware Screening (MF-CA…

## 关键点

- Simulation-driven design optimization requires active learning strategies that efficiently combine models with different computational costs and levels of fidelity.
- We introduce Multifidelity Cost-Aware Screening (MF-CAS), which enables the joint selection of sampling location and fidelity using a surrogate that provides decomposed uncertainty intervals rather than a complete predi…
- MF-CAS exploits the contribution of each fidelity to the high-fidelity uncertainty together with its computational cost to determine whether a candidate should first be evaluated at low fidelity or directly progressed t…

## 全文

Simulation-driven design optimization requires active learning strategies that efficiently combine models with different computational costs and levels of fidelity. We introduce Multifidelity Cost-Aware Screening (MF-CAS), which enables the joint selection of sampling location and fidelity using a surrogate that provides decomposed uncertainty intervals rather than a complete predictive probability distribution. MF-CAS exploits the contribution of each fidelity to the high-fidelity uncertainty together with its computational cost to determine whether a candidate should first be evaluated at low fidelity or directly progressed towards high fidelity. The method is assessed on the constrained 14-dimensional hydrodynamic optimization of the DTMB 5415 hull under a deliberately limited computational budget. MF-CAS achieves an approximately 9.0% resistance reduction, compared with 6.7% for the best baseline optimisation method, demonstrating that incorporating fidelity-resolved uncertainty directly into the joint location-fidelity decision can substantially improve multifidelity active learning efficiency.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d1e42b21e94fd356c8d2fc5d