Timezone: »

Provable Gaussian Embedding with One Observation
Ming Yu · Zhuoran Yang · Tuo Zhao · Mladen Kolar · Zhaoran Wang

Thu Dec 06 07:45 AM -- 09:45 AM (PST) @ Room 210 #19

The success of machine learning methods heavily relies on having an appropriate representation for data at hand. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about data. However, recently there has been a surge in approaches that learn how to encode the data automatically in a low dimensional space. Exponential family embedding provides a probabilistic framework for learning low-dimensional representation for various types of high-dimensional data. Though successful in practice, theoretical underpinnings for exponential family embeddings have not been established. In this paper, we study the Gaussian embedding model and develop the first theoretical results for exponential family embedding models. First, we show that, under a mild condition, the embedding structure can be learned from one observation by leveraging the parameter sharing between different contexts even though the data are dependent with each other. Second, we study properties of two algorithms used for learning the embedding structure and establish convergence results for each of them. The first algorithm is based on a convex relaxation, while the other solved the non-convex formulation of the problem directly. Experiments demonstrate the effectiveness of our approach.

Author Information

Ming Yu (The University of Chicago, Booth School of Business)
Zhuoran Yang (Princeton University)
Tuo Zhao (Gatech)
Mladen Kolar (University of Chicago)
Zhaoran Wang (Princeton, Phd student)

More from the Same Authors