Fast Latent Variable Models for Inference and Visualization on Mobile Devices

In this project we outline Vedalia, a high performance distributed network for performing inference on latent variable models in the context of Amazon review visualization. We introduce a new model, RLDA, which extends Latent Dirichlet Allocation (LDA) (Blei et al., 2003) for the review space by incorporating auxiliary data available in online reviews to improve modeling while simultaneously remaining compatible with preexisting fast sampling techniques such as (Yao et al., 2009; Li et al., 2014a) to achieve high performance. The network is designed such that computation is efficiently offloaded to the client devices using the Chital system (Robinson & Li, 2015), improving response times and reducing server costs. The resulting system is able to rapidly compute a large number of specialized latent variable models while requiring minimal server resources.