Brian Kulis


Associate Professor
Department of Electrical and Computer Engineering
Department of Computer Science
Division of Systems Engineering
Boston University
Boston, MA


What's New

  • New paper accepted to NeurIPS 2020: "Learning to Approximate a Bregman Divergence"
  • 3 papers accepted to Interspeech 2020 (links coming soon)
  • New paper accepted to ECCV 2020: "Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer" (with Xide Xia, Meng Zhang, Tianfan Xue, Zheng Sun, Hui Fang, and Jiawen Chen). Arxiv link here
  • New paper accepted to ICML 2020: "Deep Divergence Learning" (with Kubra Cilingir and Rachel Manzelli). Arxiv link here
  • New paper accepted to ICML 2020: "Piecewise Linear Regression via a Difference of Convex Functions" (with Ali Siahkamari, Aditya Gangrade, and Venkatesh Saligrama)
  • I am spending the academic year 2019-20 at Amazon, working on machine learning for Alexa.
  • New paper on arXiv (with Ali Siahkamari, David Castanon, and Venkatesh Saligrama): "Learning Bregman Divergences," posted here.

  • Introduction

    I am an associate professor in the Department of Electrical and Computer Engineering and the Department of Computer Science at Boston University, as well sa a core member of the Division of Systems Engineering. I also work at Amazon as an Amazon Scholar in Alexa. From 2015-2018 I was the Peter J. Levine Career Development Assistant Professor in ECE and CS at Boston University, and from 2012-2015 I was an assistant professor in the Department of Computer Science and Engineering and the Department of Statistics at Ohio State University.

    Before that, I spent three years as a postdoc at UC Berkeley EECS (Computer Science Division), and was also affiliated with ICSI, where I had the good fortune to work with Trevor Darrell, Stuart Russell, Michael Jordan, and Peter Bartlett. Broadly speaking, I am interested in all aspects of machine learning, with an emphasis on applications to computer vision. Most of my research focuses on making it easier to analyze large-scale data. A major focus is on large-scale optimization for core problems in machine learning such as metric learning, content-based search, clustering, and online learning. I am also interested in large-scale graphical models, Bayesian inference, Bayesian nonparametrics, and deep learning.

    I finished my Ph.D. in computer science in November, 2008, supervised by Inderjit Dhillon in the University of Texas at Austin computer science department. I did my undergrad in computer science and mathematics at Cornell University. I have also worked with John Platt and Arun Surendran at Microsoft Research on large-scale optimization, and as an undergraduate, I worked with John Hopcroft on tracking topics in networked data over time. During the Fall 2007 semester, I was a research fellow at the Institute for Pure and Applied Mathematics at U.C.L.A.


    Curriculum Vitae [pdf]


    Recent Service

  • Area Chair: AISTATS 2021
  • (Senior) Area Chair: AAAI 2021
  • Area Chair: ICLR 2021
  • Area Chair: NeurIPS 2020
  • Area Chair: ICML 2020
  • Area Chair: AISTATS 2020
  • (Senior) Area Chair: AAAI 2020
  • Area chair: NeurIPS 2019
  • Area chair: ICML 2019
  • Area chair: AISTATS 2019
  • Area chair: NIPS 2018
  • Area chair: ICML 2018
  • Senior Program Committee: AAAI 2018
  • Area chair: NIPS 2017
  • Area chair: ICML 2017
  • Area chair: AISTATS 2017
  • Area chair: ICML 2016
  • Area chair: AISTATS 2016
  • Area chair: ICML 2015
  • Area chair: AISTATS 2015
  • Area chair: NIPS 2014
  • Area chair: ICML 2014
  • Local arrangements chair: CVPR 2014
  • Area chair: ICML 2013

  • Publications by Type

    Publications Chronologically

    Google scholar profile


    Teaching

  • Fall, 2020. Deep Learning
  • Spring, 2019. Introduction to Machine Learning
  • Fall, 2018. Deep Learning
  • Spring, 2018. Advanced Data Structures and Algorithms
  • Spring, 2017. Deep Learning
  • Spring, 2017. Advanced Data Structures and Algorithms
  • Fall, 2016. Advanced Data Structures and Algorithms
  • Spring, 2015. Bayesian Modeling and Inference
  • Fall, 2014. Survey of Artificial Intelligence II
  • Spring, 2014. Survey of Artificial Intelligence II
  • Spring, 2013. Machine Learning
  • Fall, 2012. Probabilistic Graphical Models
  • Spring, 2012. Bayesian Modeling and Inference

  • Current Students

  • Andrew Cutler, PhD student
  • Kubra Cilingir, PhD student
  • Ali Siahkamari, PhD student
  • Xide Xia, PhD student

  • Former Group Members

  • Natasha Frumkin, BS. After BU: PhD student, UT Austin
  • Tayler Pauls, MS. After BU: Stealth Startup
  • Vijay Thakkar, BS. After BU: Graduate student, Georgia Tech.
  • Rachel Manzelli, BS. After BU: Marlo Inc.
  • Siva Sankarapandian, MS. After BU: Proscia Inc.
  • Robert Finn, PhD. After OSU: Assistant Professor, St. Peters University.
  • Anirban Roychowdhury, PhD. After OSU: Research Scientist at Facebook.
  • Ke Jiang, PhD. After OSU: Data Scientist at Microsoft.
  • Xiangyang Xhou, MS. After OSU: Google.
  • Lizzy Burl, BS. After OSU: Google.
  • Jiaxin Zhang, MS. After OSU: Google.
  • Ye Liu, MS. After OSU: PhD student, University of Michigan.
  • Siddharth Singh, MS. After OSU: IBM, then Amazon.

  • Research Details

    Click here to read more about some of my research.


    Contact Info

    Office: 441 PHO

    Email: bkulis [at] bu [dot] edu