Poster
A Non-generative Framework and Convex Relaxations for Unsupervised Learning
Elad Hazan · Tengyu Ma

Mon Dec 5th 06:00 -- 09:30 PM @ Area 5+6+7+8 #45 #None
in Monday Posters »

We give a novel formal theoretical framework for unsupervised learning with two distinctive characteristics. First, it does not assume any generative model and based on a worst-case performance metric. Second, it is comparative, namely performance is measured with respect to a given hypothesis class. This allows to avoid known computational hardness results and improper algorithms based on convex relaxations. We show how several families of unsupervised learning models, which were previously only analyzed under probabilistic assumptions and are otherwise provably intractable, can be efficiently learned in our framework by convex optimization.

Keywords: Learning Theory · (Other) Unsupervised Learning Methods

Author Information

Elad Hazan (Princeton University)
Tengyu Ma (Princeton University)

More from the Same Authors