arXiv：cs.LG· Aapo Hyv\"arinen·· 3 小时前
无监督机器学习的目标是什么？Aapo Hyvärinen 提出四类目标
What is the goal of unsupervised machine learning?
AI 导读
Aapo Hyvärinen 在 arXiv 发表观点文章，认为无监督学习是一个异质领域，无法用单一目标定义，并提出四类目标：估计数据分布、生成新数据点、为下游任务提取特征、理解数据。文章指出这与监督学习和强化学习不同，试图为无监督学习定义单一目标是徒劳的。
正文
Abstract:Unsupervised learning is one of the main branches of machine learning. Here I argue that unlike the other branches of machine learning (supervised and reinforcement learning), unsupervised learning is a rather heterogenous field that can serve several different goals. It seems futile to try to define one single goal for unsupervised learning. I identify four different goals for unsupervised learning: 1) Estimating the distribution, 2) Generating new data points, 3) Extracting features for downstream tasks, and 4) Understanding the data.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.11697 [cs.LG] |
| (or arXiv:2610.11697v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11697 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aapo Hyvärinen [view email]
[v1]
Thu, 8 Oct 2026 11:07:04 UTC (33 KB)
来源：arXiv：cs.LG · arxiv.org