Date of this Version
Proceedings of the 13th International Conference on Artificial Intelligence and Statistics
The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model. A central issue is learning these models in high-dimensions when the optimal parameter vector is sparse. This work characterizes a certain strong convexity property of general exponential families, which allows their generalization ability to be quantified. In particular, we show how this property can be used to analyze generic exponential families under L1 regularization.
Kakade, S. M., Shamir, O., Sridharan, K., & Tewari, A. (2010). Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity. Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, 9 381-388. Retrieved from https://repository.upenn.edu/statistics_papers/134
Date Posted: 27 November 2017
This document has been peer reviewed.