Sparse Three-parameter Restricted Indian Buffet Process for Understanding International Trade
This provides a method for analyzing countries' economic structures, but it is incremental as it builds on existing processes for sparse matrix factorization.
The paper tackled the problem of exploratory analysis of high-dimensional count data, such as international trade, by developing a Bayesian nonparametric latent feature model that combines three-parameter and restricted Indian buffet processes, resulting in better approximation of input distributions and easier-to-interpret topics.
This paper presents a Bayesian nonparametric latent feature model specially suitable for exploratory analysis of high-dimensional count data. We perform a non-negative doubly sparse matrix factorization that has two main advantages: not only we are able to better approximate the row input distributions, but the inferred topics are also easier to interpret. By combining the three-parameter and restricted Indian buffet processes into a single prior, we increase the model flexibility, allowing for a full spectrum of sparse solutions in the latent space. We demonstrate the usefulness of our approach in the analysis of countries' economic structure. Compared to other approaches, empirical results show our model's ability to give easy-to-interpret information and better capture the underlying sparsity structure of data.