CompSust Open Graduate Seminar (COGS)
The COGS will focus on disseminating work of graduate students in the computational sustainability network. The format will be short (~30 minute) presentations with plenty of time for open discussion. All are welcome to attend. The series is sponsored by CompSustNet, with support from the National Science Foundation's Expeditions in Computing program.
The COGS Program Committee includes: Sebastian Ament (Cornell), Nirma Dolatnia (OSU), Priya Donti (CMU), Amrita Gupta (GATech), Neal Jean (Stanford), Bryan Wilder (USC), and Kevin Winner (UMass).
For information about previous semesters, please see the past COGS list.
See also the Computational Sustainability Virtual Seminar Series.
|Fri Sep 21, 2018, 1:30-2:30pm EDT (UTC-4)||Di Chen, Cornell University||End-to-End learning for the Deep Multivariate Probit Model|
Di Chen, Cornell University
Fri Sep 21, 2018, 1:30-2:30pm EDT (UTC-4)
Title: End-to-End learning for the Deep Multivariate Probit Model
Abstract: Understanding multi-entity interactions is a central question in many real-world applications. For example, in computational sustainability, it is important to understand the spatial distribution of species and how species interact with each other and their environment, for developing conservation plans. In computer vision, the detections of multiple objects are often correlated because of the shared background and scenario. In natural language processing, a text often has several correlated labels in terms of its topic, emotion, and semantic meaning.
The multivariate probit model (MVP) is a popular classic model for studying binary responses of multiple entities. Nevertheless, the computational challenge of learning the MVP model, given that its likelihood involves integrating over a multi-dimensional constrained space of latent variables, significantly limits its application in practice.
In this talk, I will present a flexible deep generalization of the classic MVP, the Deep Multivariate Probit Model (DMVP), which is an end-to-end learning scheme that uses an efficient parallel sampling process of the multivariate probit model to exploit GPU-boosted deep neural networks. We show that when applied to multi-entity modelling problems, which are natural DMVP applications, DMVP trains faster than classical MVP, by at least an order of magnitude, captures rich correlations among entities, and further improves the joint likelihood of entities compared with several competitive models.
The talk will run about 30 minutes, with an extended 20 minutes question and discussion segment following the talk. I released my code on the bitbucket and you are welcome to use DMVP to explore the interesting multi-entity correlation in your own domain.
Bio: Di Chen is a second-year Ph.D. student in the Department of Computer Science at Cornell University, advised by Carla P. Gomes. His research includes solving structured prediction, multi-entity modeling and covariate shift using state-of-the-art deep learning techniques.