arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.00474cs.LGeess.SP
收藏

关于图信号的最优恢复

On the Optimal Recovery of Graph Signals

Texas A&M University(得克萨斯农工大学)

Simon Foucart, Chunyang Liao, Nate Veldt

AI总结:

本文从最优恢复视角研究图信号学习,提出计算最优或近最优正则化参数的方法,为图学习中的经典优化技术提供新解释,并通过半合成数据集实验验证其潜力。

摘要:

从部分观测数据中学习平滑图信号是图机器学习中一个被广泛研究的任务。我们从最优恢复的视角来考虑这一任务,最优恢复是一种从观测数据中学习函数的数学框架,它采用与待学习函数的模型假设相关联的最坏情况视角。最优恢复文献中的早期工作已经表明,最小化正则化目标可以为一大类问题产生最优解,但并未完全确定正则化参数。我们的主要贡献提供了一种计算最优或接近最优(取决于具体设置)正则化参数的方法,专门针对图信号处理问题。我们的结果为图学习中的经典优化技术提供了新的解释,并为超参数选择带来了新的见解。我们在多个半合成图信号处理数据集上的数值实验中展示了所提方法的潜力。

英文摘要:

Learning a smooth graph signal from partially observed data is a well-studied task in graph-based machine learning. We consider this task from the perspective of optimal recovery, a mathematical framework for learning a function from observational data that adopts a worst-case perspective tied to model assumptions on the function to be learned. Earlier work in the optimal recovery literature has shown that minimizing a regularized objective produces optimal solutions for a general class of problems, but did not fully identify the regularization parameter. Our main contribution provides a way to compute regularization parameters that are optimal or near-optimal (depending on the setting), specifically for graph signal processing problems. Our results offer a new interpretation for classical optimization techniques in graph-based learning and also come with new insights for hyperparameter selection. We illustrate the potential of our methods in numerical experiments on several semi-synthetic graph signal processing datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑