Algorithmic Foundations of Data Science Institute
UW got an NSF Tripods grant! We are have started an institute on the theoretical
foundations of data science.
My research focuses on the rigorous foundations of
statistical and computational learning in a diverse set of
paradigms, ranging from neuroscience (my graduate work started with examining the neural
and psychological basis of animal and human learning) to machine
learning (and reinforcement learning) to learning in game-theoretic
and economic settings.
Machine learning is enjoying tremendous advances, and
my group's research objectives are to aid in these collective efforts to rapidly
advance progress on core scientific, technological, and AI
these ends, much of my work is in the balance between provably
efficient methods (both from a statistical and computational perspective) and
practically effective methods. Some of my recent research
- pratical and provably efficient methods for large scale
optimization, which address statistical issues and non-convexity (see here, here and here).
- learning in structured settings, such as estimating latent
variable models, memory models, etc. (see here, here, and here).
- specific application domains (e.g. music
enjoy collaborating with researchers, across
a variety of different areas (including statistics, computer science,
signal processing, AI application domains, social sciences, economics, psychology, and biology/neuroscience).
Sham Kakade is a Washington
Research Foundation Data Science Chair, with a joint appointment in
of Statistics and the Department
of Computer Science at the University of
From 2011-2015, I was a principal research scientist at Microsoft
Research, New England. From 2010-2012, I was an associate professor at the Department of
Statistics, Wharton, University of Pennsylvania. From 2005-2009, I was an assistant professor at the Toyota Technological Institute at
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. I was a
postdoc in the Computer and
Information Science department at the University of Pennsylvania
under the supervision of Michael Kearns.
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.
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.
Tensor Decompositions for Learning Latent Variable Models, AAAI 2014
Tensor Decompositions Methods for Learning Latent Variable Models, ICML 2013
CSE 446: Machine Learning, Winter 2018
CSE 547 / STAT 548: Machine Learning for Big Data, Spring 2017
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
Ramya Korlakai Vinayak
Gabriel Cadamuro (co-advised with
(in reverse chronological order)
Daniel Hsu (while at TTI-C)
Sathyanarayan Anand (while at TTI-C)
Email: sham [at] cs [dot] washington [dot] edu
CSE office address:
Computer Science & Engineering, Office 436
Paul Allen Center
Stat office address:
Department of Statistics, Office 303
University of Washington
Seattle, WA 98195