David Blei and Co-Authors Receive Test of Time Award during NeurIPS

Columbia University statistics and computer science professor David Blei and co-authors Matthew Hoffman (Princeton University) and Francis Bach (Ecole Normale Supérieure) were recognized with a Test of Time Award during NeurIPS, which is the world’s top machine learning conference.

In their landmark paper, Online Learning for Latent Dirichlet Allocation, Blei, Hoffman, and Bach introduced a stochastic variational gradient based inference procedure for training Latent Dirichlet Allocation (LDA) models on very large text corpora. On the theoretical side, it is shown that the training procedure converges to a local optimum and that the simple stochastic gradient updates correspond to a stochastic natural gradient of the evidence lower bound objective. On the empirical side, the authors demonstrated that LDA can be comfortably trained on text corpora of several hundreds of thousands of documents, making it a practical technique for “big data” problems. This represents the first stepping stone for general stochastic gradient variational inference procedures for a much broader class of models.

Blei’s research involves probabilistic topic models, Bayesian nonparametric methods, and approximate posterior inference. He works on a variety of applications, including text, images, music, social networks, user behavior, and scientific data. He earned his Ph.D. in computer science from the University of California, Berkeley, and before Columbia, he was an associate professor of computer science at Princeton University. He has received several awards for his research, including a Sloan Fellowship, Office of Naval Research Young Investigator Award, Presidential Early Career Award for Scientists and Engineers, and Blavatnik Faculty Award.

Blei serves on the Data Science Institute‘s executive committee. He is also a member of the Computational Social Science working group and the Foundations of Data Science and Computing Systems for Data-Driven Science centers.

Read More: They Found a Way to Thematically Sort All of Wikipedia on a Laptop