9/21/2017 | 4:15pm | E51-335
Reception to follow.
Andrew Li
PhD Student
Operations Research Center, MIT
Abstract: Product and content personalization is now ubiquitous in e-commerce. There is typically too little available transactional data for this task. As such, companies today seek to use a variety of information on the interactions between a product and a customer to drive personalization decisions. We formalize this problem as one of recovering a large-scale matrix, with side information in the form of additional matrices of conforming dimension. Viewing the matrix we seek to recover and the side information we have as slices of a tensor, we consider the problem of Slice Recovery, which is to recover specific slices of ‘simple’ tensors from noisy observations of the entire tensor. We propose a definition of simplicity that on the one hand elegantly generalizes a standard generative model for our motivating problem, and on the other subsumes low-rank tensors for a variety of existing definitions of tensor rank. We provide an efficient algorithm for slice recovery that is practical for massive datasets and provides a significant performance improvement over state of the art incumbent approaches to tensor recovery. Further, we establish near-optimal recovery guarantees that in an important regime represent an order improvement over the best available results for this problem. Experiments on data from a music streaming service demonstrate the performance and scalability of our algorithm. (Joint work with Prof. Vivek Farias.)
Bio: Andrew Li is a PhD candidate in the Operations Research Center at MIT, advised by Vivek Farias. Before joining MIT, he earned a BS in Operations Research from Columbia University. His primary research interest is in the design and analysis of data-driven solutions to contemporary, large-scale problems in operations management.