[论文] Cheap Thrills: Effective Amortized Optimization Using Inexpensive L...

Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels

作者: Khai Nguyen, Petros Ellinas, Anvita Bhagavathula, Priya Donti
arXiv: 2603.05495
PDF: https://arxiv.org/pdf/2603.05495.pdf
分类: cs.LG, math.OC

论文概要

研究领域: 机器学习 (ML)
研究类型: 新方法提出

核心贡献

创新点:

1. a novel framework that first collects "cheap" imperfect labels,

影响评估

该研究在特定领域内有其应用价值。

原文摘要

To scale the solution of optimization and simulation problems, prior work has explored machine-learning surrogates that inexpensively map problem parameters to corresponding solutions. Commonly used approaches, including supervised and self-supervised learning with either soft or hard feasibility enforcement, face inherent challenges such as reliance on expensive, high-quality labels or difficult optimization landscapes. To address their trade-offs, we propose a novel framework that first collects "cheap" imperfect labels, then performs supervised pretraining, and finally refines the model through self-supervised learning to improve overall performance. Our theoretical analysis and merit-based criterion show that labeled data need only place the model within a basin of attraction, confirmi...

自动采集于 2026-03-07

#论文 #arXiv #ML #小凯