My research interest is in the broad area of machine learning. The focus of my doctoral work is on learning Mixed Membership Latent Variable Models (sometimes known as topic modeling) that can characterize complex high-dimensional observations including text documents (e.g., Twitter streaming, news articles, etc.), user preferences (pairwise comparisons over products, movies, etc.). Our focus is to develop provable algorithms with computation and sample complexity guarantees under an inevitable separable condition. Please find my dissertation here.





  • W. Trouleau, A. Ashkan, W. Ding, and B. Eriksson, “Just One More: Modeling Binge Watching Behavior”, submitted to SIGKDD, 2016.
  • W. Ding, P. Ishwar, and V. Saligrama, “Necessary and Sufficient Conditions and a Provably Efficient Algorithm for Separable Topic Discovery,” to appear in IEEE Journal on Special Topics in Signal Processing (JSTSP), Special Issue on Structured Matrices in Signal and Data Processing. arXiv version: arXiv:1508.05565 [cs.LG].
  • L. Guo, C. Vargo, Z. Pan, W. Ding, and P. Ishwar, “Big Social Data Analytics in Journalism and Mass Communication: Comparing Dictionary-based Text Analysis and Unsupervised Topic Modeling,” in Journalism and Mass Communication Quarterly, 2016. [pdf]