Hello, Friend.

Matus Telgarsky

mjt at illinois dot edu

2016 - (!). Assistant Professor, Computer Science, UIUC.
Spring 2017. Research Fellow, Simons-Berkeley Institute.
2014 - 2016. Postdoc in EECS, University of Michigan. Host: Jake Abernethy.
2013 - 2014. Consulting Researcher at MSR NYC. Host: John Langford.
2013 - 2014. Postdoc in Statistics, Rutgers University. Host: Tong Zhang.
2007 - 2013. PhD in Computer Science, UCSD. Advisor: Sanjoy Dasgupta.
2004 - 2007. BS in Computer Science & Discrete Math, CMU.
2001 - 2003. Diploma in Violin Performance, Juilliard. Teacher: Joel Smirnoff.

Selected papers
Greedy bi-criteria approximations for \(k\)-medians and \(k\)-means.
Daniel Hsu, Matus Telgarsky.
[arXiv] Benefits of Depth in Neural Networks.
Matus Telgarsky.
[arXiv] [10min video] Convex Risk Minimization and Conditional Probability Estimation.
Matus Telgarsky, Miroslav Dudík, Robert Schapire.
[arXiv] [short video] [poster] Moment-based Uniform Deviation Bounds for \(k\)-means and Friends.
Matus Telgarsky, Sanjoy Dasgupta.
[pdf] [arXiv] [poster] Margins, Shrinkage, and Boosting.
Matus Telgarsky.
[arXiv] [video] Agglomerative Bregman Clustering.
Matus Telgarsky, Sanjoy Dasgupta.
[pdf] [short video] Full list of papers.

Fall 2016: CSE 598 Tel, Machine Learning Theory.

I used to play the violin;
I coded a screensaver, a 3-d plotting tool, and a few other things if you know where to look;
my desk is always messy;
I like scifi books, pencils, ramen, and aphex twin.