K-means as feature extraction: a degenerate mixture of factor analyzers view
caglar_ee · x · 2026-11-12
A technical exchange: caglaree argues that the feature-extractor extension of K-means corresponds to unsupervised learning, and can be seen as a very simple version of a Mixture of Factor Analyzers (MFA) — except the model only makes sense when the variational posteriors are coupled with additional constraints. He adds this lets you use K-means for supervised learning, and since self-supervised learning is mathematically a form of supervised learning, the same approach applies there too.
More from Research
- HipKittens turns one: breaking AMD's 'CUDA moat' for a multi-silicon future — simran_s_arora · 2026-11-12
- Why world model teams pay for gameplay with inputs attached: actions are the scarce half — KnowledgeOk7634 · 2026-11-12
- Uno uses discrete diffusion for up to 3x lossless LLM inference speedup, talk Nov 13 — burny_tech · 2026-11-12
- Pro-0 trains dexterous robot hands from human demos with zero on-robot data — chris_j_paxton · 2026-11-12
- Physical Intelligence clarifies: zero-shot LLM already beats fine-tuned open VLA — paigeinsf · 2026-11-12
- Zero-shot LLM Fable beats fine-tuned pi0.5 VLA on memory tasks 64 vs 7 — paigeinsf · 2026-11-12