Sham M. Kakade

Washington Research Foundation Data Science Chair

Senior Data Science Fellow,
UW eScience Institute.

Associate Professor in both:
Department of Statistics
Department of Computer Science

Adjunct Professor in:
Department of Electrical Engineering

University of Washington


News:

MusicNet is out!
We have released the MusicNet dataset to the machine learning and music communities as a resource for training models and a common benchmark for comparing results. MusicNet is a collection of 330 freely-licensed classical music recordings, together with over 1 million annotated labels indicating the precise time of each note every recording, the instrument that plays each note, and the note's position in the metrical structure of the composition. The labels are acquired from musical scores aligned to recordings by dynamic time warping.
There is more info on the MusicNet website. Also, some press is here.
Foundations of Machine Learning 2017
We are putting together a machine learning semester at the Simons Institute in Berkeley from Jan to May, 2017. We are seeking to bring together a range of researchers to help develop novel and effective algorithms.

Publications  


About me:

See my Official Bio for publicity purposes.
Sham Kakade is a Washington Research Foundation Data Science Chair, with a joint appointment in the Department of Statistics and the Department of Computer Science at the University of Washington.
I completed my PhD at the Gatsby Computational Neuroscience Unit under the supervision of Peter Dayan, and I was an undergraduate at Caltech where I obtained my BS in physics. Before joining UW, I was a principal research scientist at Microsoft Research, New England. Previous to this, I was an associate professor at the Department of Statistics, Wharton, University of Pennsylvania (from 2010-2012), and I was an assistant professor at the Toyota Technological Institute at Chicago (from 2005-2009). I was a postdoc in the Computer and Information Science department at the University of Pennsylvania under the supervision of Michael Kearns.

Research

My research focuses on both theoretical and applied questions in machine learning and artificial intelligence. My hope is to help to advance the state of the art on core scientific, technological, and AI problems in the near future. I enjoy collaborating with researchers, across a variety of different areas (including statistics, computer science, signal processing, social sciences, economics, psychology, and biology/neuroscience).
Here are a few of my recent research interests: My recent theoretical work focusses on developing computationally efficient algorithms (both provably so and in practice) for large scale learning problems, where I think about convex and non-convex issues along with issues related to statistical efficiency. I have also been actively working on applied problems in music, computer vision, and robotics. Some of the challenges I am thinking about in these applied areas are representational(e.g. how to develop appropriate architectures) and some are computational (e.g. how to develop faster optimization algorithms, say for deep learning methods).

Prospective Students

If you are interested in machine learning, optimization, statistics, CS theory, or related areas, please apply either through the computer science website or statistics website. UW is a great place for these activities.

Some good stuff at UW:

Data Science
Machine Learning
CS Theory
Artificial Intelligence

Some Activities and Services

Co-organizer for the Simons Foundations of Machine Learning, Winter, 2017
Co-chair for the Simon's Representational Learning workshop, March, 2017
Co-chair for the IMS-MSR Workshop: Foundations of Data Science, June 11th, 2015.
Steering committee for the fourth New England Machine Learning Day, May 18th, 2015.
Program committee for the third New England Machine Learning Day, May 13th, 2014.
Co-chair for New York Computer Science and Economics Day V, Dec 3rd, 2012.
Program committee for the first New England Machine Learning Day, May 16th, 2012.
Program chair for the 24th Annual Conference on Learning Theory (COLT 2011) which took place in Budapest, Hungary, on July 9-11, 2011.

Tutorials

Tensor Decompositions for Learning Latent Variable Models, AAAI 2014
Tensor Decompositions Methods for Learning Latent Variable Models, ICML 2013

Course Links

CSE 546: Machine Learning, Autumn 2016
CSE 547 / STAT 548: Machine Learning for Big Data, Spring 2016
CSE 546: Machine Learning, Autumn 2015
Stat 928: Statistical Learning Theory
Stat 991: Multivariate Analysis, Dimensionality Reduction, and Spectral Methods
Large Scale Learning
Learning Theory

Current Students

Gabriel Cadamuro (co-advised with Josh Blumenstock)
Rahul Kidambi
Krishna Pillutla
Aravind Rajeswaran (co-advised with Emo Todorov)
John Thickstun (co-advised with Zaid Harchaoui)

Former Postdocs

Daniel Hsu (while at UPenn)
Karthik Sridharan

Former Interns (in reverse chronological order)

Chi Jin
Aaron Sidford
Roy Frostig
David Belanger
Chen Wang
Qingqing Huang
Jaehyun Park
Karl Stratos
Do-kyum Kim
Praneeth Netrapalli
Rashish Tandon
Rong Ge
Adel Javanmard
Matus Telgarsky
Daniel Hsu (while at TTI-C)
Sathyanarayan Anand (while at TTI-C)

Contact Info

Email: sham [at] cs [dot] washington [dot] edu

Department of Statistics, Office 303
Padelford Hall

Computer Science & Engineering, Office 436
Paul Allen Center

University of Washington
Seattle, WA 98195