What is the goal of unsupervised machine learning?
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 2 of its 44 references that are in the map. First posted on arXiv 8 Oct 2026.
Builds on
2 of 44 references.
References · 2
- 2021How to Train Your Energy-Based Modelscited by 274
- 2025Better Decisions through the Right Causal World Modelcited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2021Understanding the World Through Action
- 2024Towards Measuring Goal-Directedness in AI Systems
- 2025On the importance of multiple training seeds for evaluating machine unlearning
- 2026Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
- 2025When unlearning is free: leveraging low influence points to reduce computational costs
- 2026Is your algorithm unlearning or untraining?
- 2024A More Practical Approach to Machine Unlearning
- 2024Towards Efficient Target-Level Machine Unlearning Based on Essential Graph