Research
synopsis: My principal research interests lie
in the development of machine learning and statistical methodology,
and large-scale computational
system and architecture, for solving problems involving automated learning,
reasoning, and decision-making in high-dimensional, multimodal, and
dynamic possible worlds in artificial, biological, and social systems.
Current Ph.D. Students and Postdocs:
Past Students and Postdocs:
- Amr
Ahmed, Research Scientist, Google
- Maruan Al-Shedivat, Principal Research Scientist, Genesis Therapeutics
- Ross Curtis, Software Engineer, AncestryDNA
- Bryon Aragam, Assistant Professor, University of Chicago
- Wei Dai, Research Engineer, Apple
- Kumar Avinava Dubey, Research Scientist, Google
- Jacob Eisenstein, Assistant
Professor, Georgia Institute of Technology
- Wenjie Fu, Software Engineer, Facebook
- Anuj Goyal, Software Engineer, LinkedIn
- Steve Hanneke, Visiting Assistant
Professor, Carnegie Mellon University
- Kamisetty
Hetunandan, Research Scientist, Facebook
- Qirong Ho, CTO, Petuum Inc.
- Judie Howrylak, Assistant Professor, Penn State University
- Zhiting Hu, Assistant Professor, UC San Diego
- Gunhee
Kim, Associate Professor, Seoul National University
- Jin Kyu Kim, Research Scientist, Facebook
- Abhimanu Kumar, Senior Research Engineer, LinkedIn
- Seyoung Kim, Associate Professor, Carnegie Mellon University
- Mladen Kolar, Assistant Professor, University of Chicago
- Lisa Lee, Research Scientist, Google
- Seunghak
Lee, Research Scientist, Facebook
- Ben Lengerich, Postdoc, MIT
- Xiaodan Liang, Associate Professor, Zhongshan University
- Andre Martins, Research Scientist, Priberam Labs and
Instituto Superior Técnico
- Micol Marchetti-Bowick, Engineering Manager, Uber
- Willie Neiswanger, PostDoctoral Fellow, Stanford University
- Ankur
Parikh, Staff research scientist at Google, adjunct assistant professor at NYU.
- Kriti
Puniyani, Research Scientist, Google
- Aurick Qiao, CEO, Petuum Inc.
- Pradipta Ray,
Research Scientist, University of Taxes Dallas
- Mrinmaya Sachan, Assistant Professor, ETH, Zurick
- Suyash Shringarpure, Senior Scientist, Statistical Genetics at 23andMe
- Kyung-Ah Sohn, Assistant Professor, Ajou University
- Le
Song, Professor, MBZUAI
- Chong
Wang, Research Scientist, Google
- Jinliang Wei, Engineer, Google
- Sinead
Williamson, Assistant Professor, University of
Texas Austin
- Andrew
Wilson, Assistant Professor, New York Unicersity
- Haohan Wang,
Assistant Professor, UIUC
- Pengtao Xie, Assistant Professor, UC San Diego
- Junming
Yin, Assistant Professor, University of
Arizona
- Yaoliang
Yu, Assistant Professor, University of Waterloo
- Bin
Zhao, Entrepreneur
- Hao Zhang, PostDoc, UC Berkeley
- Xun Zheng, Research Scientist, Uber
- Bing Zhao, Research Scientist, SRI
- Jun Zhu, Professor, Tsinghua University
Recent
Activities:
Research and Development:
On June 11th, 2020, we launched the
CASL (Composible, Automatic, and Scable ML)
open source consortium that brings our research and development at Petuum Inc., CMU Sailing Lab, and collaborating labs on Distributed ML (e.g.,
AutoDist,
AdaptDL,
Alpa),
Automated ML (e.g.,
Dragonfly,
ProBO),
and Composable ML (e.g.,
Texar,
Forte)
implemented across PyTorch and TensorFlow under a unified umbrella for a Production and Industrial AI Platform.
Teaching:
I taught Graduate Introduction to Machine Learning
(10701) again in Fall 2020, with Professor Ziv Bar-Joseph
I have been teaching Probabilistic Graphical Models
(10708), an advanced graduate course on theory, algorithm, and application for multivariate modeling, inference, and deep learning since 2005 at CMU. All the past versions are available here.
Video lectures of Probabilistic Graphical Models (10708):
2014,
2019,
2020.
Tutorials and Talks:
From Learning, to Meta-Learning, to "Lego-Learning -- A pathway toward autonomous AI
[video][slides], CMU AI Seminar, 2022.
It is time for deep learning to understand its expense bills
[video], KDD Deep Learning Day 2021.
Learning-to-learn through Model-based Optimization: HPO, NAS, and Distributed Systems
[video], ACL 2021 workshop on Meta Learning and Its Applications to Natural Language Processing.
A Data-Centric View for Composable Natural Language Processing
[video1] [video2], ICML 2021 Machine Learning for Data Workshop.
Simplifying and Automating Parallel Machine Learning via a Programmable and Composable Parallel ML System
[slides]
[video],
Tutorial, AAAI 2021.
From Performance-oriented AI to Production- and Industrial-AI
[video],
Michigan Institute for Data Science, 2020.
A Blueprint of Standardized and Composable Machine Learning
[slides]
[video],
Institute for Advanced Study, Princeton, 2020.
Learning from All Types of Experiences:
A Unifying Machine Learning Perspective
[slides]
[video],
Tutorial, KDD 2020.
Compositionality in Machine Learning
[slides]
[video],
Open Data Science Conference (ODSC) West 2019.
A Civil Engineering Perspective on Artificial Intelligence From Petuum
[slides],
Distinguished Lectures in Computational Innovation, Columbia University, 2018.
PetuumMed: algorithms and system for EHR-based medical decision support
[slides], MIT, 2018.
A Statistical Machine Learning Perspective of Deep Learning: Algorithm, Theory, and Scalable Computing
[slides],
tutorial at the International Summer School on Deep Learning, Genova, Italy, 2018.
Strategies & Principles for Distributed Machine Learning
[slides],
[video],
Allen Institute for AI, 2016.
Services:
Board Member, The International Machine Learning Society
.
Program Committee Chair, ICML
2014.
General Chair, ICML 2019.
Action Editor/Associate Editor: JASA, AOAS,
JMLR, MLJ, and PAMI.
|
