Skip to main content

A non-generative framework and convex relaxations for unsupervised learning

Author(s): Hazan, Elad; Ma, T

To refer to this page use:
Abstract: 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
Publication Date: 2016
Citation: Hazan, E, Ma, T. (2016). A non-generative framework and convex relaxations for unsupervised learning. 3314 - 3322
Pages: 3314 - 3322
Type of Material: Conference Article
Journal/Proceeding Title: Advances in Neural Information Processing Systems
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.