---
title: "Exponential Family Hybrid Semi-Supervised Learning"
authors:
  - "Arvind Agarwal"
  - "Hal Daumé III"
doi: ""
url: "https://ijcai.org/proceedings/2009/165"
pdf: "https://ijcai.org/proceedings/2009/0165.pdf"
venue: "Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence"
year: 2009
pages: "974-978"
track: ""
keywords:
---

# Exponential Family Hybrid Semi-Supervised Learning

Arvind Agarwal, Hal Daumé III

*Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence*, pages 974-978.

## Abstract

We present an approach to semi-supervised learning based on an exponential family characterization. Our approach generalizes previous work on coupled priors for hybrid generative/discriminative models. Our model is more flexible and natural than previous approaches. Experimental results on several data sets show that our approach also performs better in practice. Arvind Agarwal, Hal Daume III