## Site menu:

**Suvrit Sra**(suvrit@gmail.com)

Laboratory for Information & Decision Systems (LIDS)

Massachusetts Institute of Technology (MIT)

Office: 32-D580; Tel: 617-253-3816

I'm a member of Machine Learning@MIT

My public calendar

Research Interests:**large-scale machine learning**, **optimization (convex, nonconvex)**, **matrix analysis**. I work on algorithms and applications in **statistics, machine learning, data mining**, **scientific computing**. Usually, I'm interested in anything **mathematical or computational!**

Here's a link to my

**CV**(updated: 15 Mar 2014).

## NEWS

- [24.06.2015];
**Preprint**on Manifold optimization for mixture models (with R. Hosseini) - [24.06.2015];
**Short Note**on A proof of Thompson's determinantal inequality*to appear in Mathematical Notes* - [23.06.2015];
**Preprint**on Variance reduction in stochastic gradient and asynchronous algorithms (with Sashank Reddy, Ahmed Hefny, Barnabas Poczos, Alex Smola) - [16.06.2015];
**Lecturing**at the MSR Summer School on Machine Learning, Bangalore

Lecture slides**are now available** - [17.05.2015];
**Paper**on Inequalities for normalized Schur functions*accepted to European Journal of Combinatorics*(my first combinatorics paper!) - [12.05.2015];
**Paper**on Operator Hlawka-like inequalities on positive definite tensors (with Wolfgang Berndt)*accepted to Linear Algebra and its Applications (LAA)* - [12.05.2015];
**Paper**on efficient randomized coordinate descent algorithms for**non separable**constrained optimization (deterministic, stochastic, asynchronous) (with Sashank Reddy, Ahmed Hefny, C. Downey, A. Dubey),*accepted to Uncertainty in Artificial Intelligence (UAI 2015)* - [26.04.2015];
**Paper**on efficiently learning determinantal point processes (with Z. Mariet).*accepted to ICML'15.*Incidentally, this paper was written during my first two weeks at MIT with an MIT student! - [04.04.2015];
**Preprint**new version of: Explicit diagonalization of an anti-triangular Cesaró matrix - [02.04.2015];
**Paper:**Official version: Conic geometric optimization with R. Hosseini, SIAM Journal on Optimization (SIOPT) is now available online. - [13.03.2015];
**Talk:**Speaking about Schur functions at the MIT Combinatorics Seminar!! - [01.03.2015];
**Preprint:**Proof of a conjecture in combinatorics:*On inequalities for normalized Schur functions* - [22.01.2015];
**Paper:**Conic geometric optimisation on the manifold of positive definite matrices (with R. Hosseini)*accepted for publication to SIAM J. Optimization* - [Jan 2015];
**Paper:**Data Modeling with the Elliptical Gamma Distribution; upcoming in AISTATS 2015 - [16.01.2015];
**Moved to MIT!**

## 2014

- [25.12.2014]; Looking for a candidate interested in working on a (paid) potentially
**high-impact and novel**industrial project**on machine learning for healthcare informatics**. Please email me if you are interested - Serving on Program Committees for ICML 2015, KDD 2015
- [21.11.2014]; Updated version of:

Conic geometric optimisation on the manifold of positive definite matrices - [17.11.2014]; Updated version of:

Hlawka-Popoviciu inequalities on positive definite tensors - [16.11.2014]; Fast total-variation toolbox now on github!
- [29.10.2014]; Some new preprints:

Efficient structured matrix rank minimization (convex optimization, compressed sensing)

Statistical inference with elliptical distributions (nonconvex optimization, mixture modeling)

Super fast modular total-variation optimization! (see also: TV webpage)

Hlawka inequalities on positive definite tensors (hypergraph cut style operator inequalities)

Completely strong superadditivity of generalized matrix functions (if you like matrix submodularity!)

Explicit diagonalization of a Cesaró/Markov matrix (min / max kernels, operator norms)

Asynchronous Parallel Block-Coordinate Frank-Wolfe (large-scale parallel convex optimization)

Randomized coordinate descent methods with linear constraints (work in progress) - [20.09.2014];
**I'm moving to MIT in January 2015!** - [29.07.2014]; Website moved to AWS
- [17.07.2014];
*New arXiv version of*

Conic geometric optimisation on the manifold of positive definite matrices - [15.06.2014];
*New ECCV 2014 Paper*

Riemannian sparse coding - [01.06.2014];
*Wow, I've already left CMU! so quickly it went by!!!* - [30.05.2014];
*New Uncertainty in AI (UAI)*paper

Fast Newton methods for the group fused lasso - [25.04.2014];
*New IEEE Transactions on Image Processing*paper

Robust sparse hashing - [13.04.2014];
*New ICML 2014 Paper*

Randomized nonlinear component analysis" - [15.03.2014]; Serving as an Area Chair for NIPS 2014
- Teaching Advanced Optimization at CMU from Jan 13 onwards!
- [02.01.2014]; Serving as Associate Editor for Optimization Methods and Software

## 2013 and older

- [27.12.2013]; new arXiv version of

*S. Sra*, "Positive definite matrices and the S-Divergence" - [11.12.2013]; new paper on
*Stochastic ADMM*coming up! (ICML) - [10.12.2013]; new arXiv version of

*S. Sra*, "Positive definite matrices and the symmetric Stein divergence" - [04.12.2013]; arXiv version of

*S. Sra, R. Hosseini*, "Conic geometric optimisation on the manifold of positive definite matrices" - [19.11.2013]; arXiv version of

*S. Jegelka, F. Bach, S. Sra*, "Reflection methods for submodular optimization" - [25.10.2013]; New paper in
*IMA J. Numerical Analysis*:

Correlation matrix nearness and completion under observation uncertainty - [05.09.2013]; I'll be an Area Chair for ICML 2014
- [05.09.2013]; I'm on the Senior PC for AISTATS 2014
- [04.09.2013]; Two papers @NIPS2013

(S. Jegelka, F. Bach, S. Sra) Reflection methods for submodular optimization

(S. Sra, R. Hosseini) Geometric optimisation for positive definite matrices - [01.09.2013]; Visiting ML Dept., School of CS, Carnegie Mellon University for 2 terms!
- [21.05.2013]; EE227A is over! Hopefully my lecture notes will be available soon!
- [15.03.2013]; Serving as an Area Chair for NIPS 2013
- [22.01.2013]; Teaching
*EE227A: Convex Optimization*, EECS, UC Berkeley - [08.12.2012]; Presented a short version of my new distance function at the
*NIPS Workshop on "Algebraic Topology and Machine Learning"* - [01.12.2012]; New paper: Similarity computations on positive definite matrices for fast nearest neighbor search.
*IEEE TPAMI* - [07.09.2012]; New paper: The multivariate Watson distribution: Maximum likelihood and other aspects" in
*J. Multivariate Analysis* - [03.09.2012]; Two papers @NIPS 2012

Large-scale nonconvex nonsmooth optimization

A new distance metric on the manifold of positive definite matrices - [24.06.2012]; Speaking @ the
*NIMS Hot Topics Workshop on Positive Matrices and Operators*at KNU, Daegu, Korea - My work on
**Metric Nearness**was selected to receive the**SIAM Outstanding Paper Prize, 2011** - My Book on
**Optimization for Machine Learning**(co-edited with S. Nowozin and S. J. Wright; Publisher: MIT Press) is available here. Here are links to Amazon and Barnes and Noble