Suvrit Sra
Photo credit: Misha Sra
Laboratory for Information & Decision Systems (LIDS)
Institute for Data, Systems, and Society (IDSS)
Massachusetts Institute of Technology
I'm a member of Machine Learning@MIT
and the Center for Statistics.

Contact Info
77 Massachusetts Ave, 32-D580, Massachusetts Institute of Technology, Cambridge, MA 02139
 suvrit at mit.edu     617-253-3816

Social Media

    profile for suvrit at MathOverflow, Q&A for professional mathematicians
Link to my old website

Research Interests

I am a computer scientist who works in machine learning and optimization. I work on several theoretical, algorithmic, and applied questions in machine learning and data science. I am interested in all aspects of optimization for ML, especially scalable convex and nonconvex optimization. I am fascinated by geometric optimization, a growing topic with lots of cool math. Beyond OPT & ML, I have a strong interest in matrix theory, differential geometry, metric geometry, probability theory, algebraic combinatorics, fixed-point theory, and several other areas in math.

Application areas and outreach

Currently I am looking at applications in finance, healthcare, and smart cities & infrastructure. I am also interested in energy, materials science, education, and other areas where data driven thinking holds great promise.

[arXiv profile]  [Google Scholar]

News

May 20   Preprint: Kronecker Determinantal Point Processes
(with Z. Mariet)
May 20   Preprint: Fast stochastic optimization on Riemannian manifolds
(with H. Zhang, S. Reddi)
May 20   Preprint: Fast Stochastic Methods for Nonsmooth Nonconvex Optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola)
May 05   Paper: On the Matrix Square Root via Geometric Optimization
Accepted to Electronic Journal on Linear Algebra (ELA)
Apr 26   Paper: First-order methods for geodesically convex optimization
(with Hongyi Zhang). Conference on Learning Theory (COLT 2016)
Apr 24   Paper: Geometric Mean Metric Learning
(with Pourya H. Zadeh, Reshad Hosseini)
International Conference on Machine Learning (ICML 2016)
Apr 24   Paper: Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms
(with Yu-Xiang Wang, Veeranjaneyulu Sadhanala, Wei Dai, Willie Neiswanger, Eric Xing)
International Conference on Machine Learning (ICML 2016)
Apr 24   Paper: Stochastic variance reduction for nonconvex optimization
(with Sashank Reddi, Ahmed Hefny, Barnabas Poczos, Alexander Smola).
International Conference on Machine Learning (ICML 2016)
Apr 24   Paper: Gaussian quadrature for matrix inverse forms with applications
(with Chengtao Li, Stefanie Jegelka).
International Conference on Machine Learning (ICML 2016)
Apr 24   Paper: Fast DPP sampling for Nyström with application to Kernel Methods
(with Chengtao Li, Stefanie Jegelka).
International Conference on Machine Learning (ICML 2016)
Apr 21   Paper: Entropic Metric Alignment for Correspondence Problems
(with Justin Solomon, Gabriel Peyré, Vladimir Kim).
Accepted to ACM SIGGRAPH 2016
Apr 07   Preprint: Combinatorial Topic Models using Small–Variance Asymptotics
(with Ke Jiang, Brian Kulis)
Mar 18   Preprint: Fast DPP sampling for Nyström with application to Kernel Methods
(with Chengtao Li, Stefanie Jegelka)
Mar 13   Preprint: Fast incremental method for smooth nonconvex optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola) [arXiv]
Feb 21   Preprint: First-order methods for geodesically convex optimization
(with Hongyi Zhang)
Feb 14   Paper: Inference and mixture modeling with the Elliptical Gamma distribution.
(with Reshad Hosseini, Lucas Theis, Matthias Bethge).
Accepted to Computational Statistics and Data Analysis (CSDA)
Feb 05   Preprint: Stochastic variance reduction for nonconvex optimization
(with Sashank Reddi, Ahmed Hefny, Barnabas Poczos, Alexander Smola). [arXiv]
Feb 02   Paper: Diversity Networks
(with Zelda Mariet).
International Conference on Learning Representations (ICLR 2016).
2016   Service: PC for DIFF-CVML'16 at CVPR 2016
2016   Teaching: 6.036 Introduction to Machine Learning
(with Tommi Jaakkola, Regina Barzilay)
Jan 21   Lecturing: Aspects of Convex, Nonconvex, and Geometric Optimization.
At Hausdorff Institute for Mathematics, Bonn, Germany.
Jan 18   Paper: Sum-of-squared logarithms inequality.
(with Lev Borisov, Patrizio Neff, and Christian Thiel).
Accepted to Linear Algebra and its Applications (LAA)
2016   Service: Area Chair for NIPS 2016, ICML 2016
2016   Service: Program Committee for KDD 2016
Jan 12   Book Chapter: Directional Statistics in Machine Learning: a brief review (submitted)
Jan 04   Visiting: Hausdorff Institute for Mathematics and participating in Math of Signal Processing

2015

2015 Served as Area Chair for AISTATS 2016
Dec 22 Paper: AdaDelay: Delay Adaptive Distributed Stochastic Optimization
(with Adams Wei Yu, Mu Li, Alexander Smola)
Accepted to Artificial Intelligence and Statistics 2016 (AISTATS'16)
Dec 22 Paper: Efficient Sampling for K-Determinantal Point Processes
(with Chengtao Li, Stefanie Jegelka)
Accepted to Artificial Intelligence and Statistics 2016 (AISTATS'16)
Dec 22 Book Chapter: Geometric Optimization in Machine Learning
(with Reshad Hosseini)
Dec 17 Preprint: (update) Riemannian dictionary learning and sparse coding
(with A. Cherian)
Dec 17 Preprint: (update) Inference and mixture modeling with the Elliptical Gamma distribution
(with Reshad Hosseini, Lucas Theis, Matthias Bethge)
Dec 16 Preprint: (update) Matrix square roots via geometric optimization
Dec 15 Book Chapter: Positive Definite Matrices: Data Representation and Applications to Computer Vision
(with Anoop Cherian)
Dec 06 Preprint: Bounds on bilinear inverse forms via Gaussian quadrature with applications
(with Chengtao Li, Stefanie Jegelka)
2015 Served on Program Committee for SIGMOD 2016
2015 Served on Program Committee for KDD 2015
2015 Served as Area Chair for ICML 2015
Nov 17 Preprint: Diversity Networks
(with Zelda Mariet)
Sep 18 Preprint: Inequalities via elementary symmetric polynomial monotonicity
Sep 07 Preprint: Efficient structured low rank minimization
(with Adams Wei Yu, Wanli Ma, Yaoliang Yu)
Sep 07 Preprint: Efficient Sampling for K-Determinantal Point Processes
(with Chengtao Li, Stefanie Jegelka)
Sep 07 Paper: on Positive definite matrices and the S-Divergence
to appear in Proceedings American Math Society (PAMS)
Sept. OPTML++: Running the OPTML++ research seminar plus reading group
Sep 04 Paper: on Manifold optimization for mixture models
accepted to NIPS 2015 (with R. Hosseini)
Sep 04 Paper: Asynchronous variance reduced stochastic gradient
accepted to NIPS 2015 (with with Sashank Reddi, Ahmed Hefny, Barnabas Poczos, Alexander Smola)
Aug 20 Preprint: on Delay sensitive distributed optimization
(with Adams Wei Yu, Mu Li, Alexander Smola)
Aug 17 Preprint: Sum-of-squared logarithms inequality
(with Lev Borisov, Patrizio Neff, and Christian Thiel)
Aug 14 Announcement! OPT2015: Optimization for Machine Learning, NIPS, Montreal is happening!
Jul 29 Preprint: Matrix square roots via geometric optimization
Jul 13 Talk: Conic geometric optimisation at ISMP, 2015
Jul 10 Preprint: Riemannian dictionary learning and sparse coding
(with Anoop Cherian)
Jun 24 Preprint Manifold optimization for mixture models
(with Reshad Hosseini)
Jun 24 Paper: A proof of Thompson's determinantal inequality
(with Minghua Lin)
Jun 23 Preprint Variance reduction in stochastic gradient and asynchronous algorithms
(with S. Reddy, A. Hefny, B. Poczos, A. Smola)
Jun 16 Lecturing at the MSR Summer School on Machine Learning, Bangalore
Lecture slides are now available
May 17 Paper: Inequalities for normalized Schur functions
accepted to European Journal of Combinatorics (my first combinatorics paper!)
May 12 Paper: Operator Hlawka-like inequalities on positive definite tensors
(with Wolfgang Berndt) to Linear Algebra and its Applications (LAA)
May 12 Paper: Efficient randomized coordinate descent algorithms for non separable constrained optimization
(with Sashank Reddi, Ahmed Hefny, C. Downey, A. Dubey); Uncertainty in Artificial Intelligence (UAI 2015)
Apr 26 Paper: Efficiently learning determinantal point processes
(with Z. Mariet). accepted to ICML'15. written during my first two weeks at MIT!
Apr 04 Preprint: (new version) Explicit diagonalization of an anti-triangular Cesaró matrix
Mar 13 Talk: Speaking about Schur functions at the MIT Combinatorics Seminar!!
Mar 01 Preprint: Proof of a conjecture in combinatorics: On inequalities for normalized Schur functions
Jan 22 Paper: Conic geometric optimisation on the manifold of positive definite matrices
(with Reshad Hosseini) accepted for publication to SIAM J. Optimization
Jan 17 Paper: Data Modeling with the Elliptical Gamma Distribution
upcoming in AISTATS 2015 (with Reshad Hosseini)
Jan 16 Started at 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
[21.11.2014]Preprint Updated version of: Conic geometric optimisation on the manifold of positive definite matrices
[17.11.2014]Preprint Updated version of: Hlawka-Popoviciu inequalities on positive definite tensors
[16.11.2014]SoftwareFast total-variation toolbox now on github!
[29.10.2014] 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]PreprintNew arXiv version of Conic geometric optimisation on the manifold of positive definite matrices
[15.06.2014]PaperRiemannian sparse coding, ECCV 2014
[01.06.2014]Wow, I've already left CMU! so quickly it went by!!!
[30.05.2014]PaperFast Newton methods for the group fused lasso, New Uncertainty in AI (UAI 2014)
[25.04.2014]PaperRobust sparse hashing, IEEE Transactions on Image Processing
[13.04.2014]PaperRandomized nonlinear component analysis (ICML 2014)
[15.03.2014]Serving as an Area Chair for NIPS 2014
Jan 2014Teaching 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]Preprint new arXiv version of Positive definite matrices and the S-Divergence
[11.12.2013]Paper Stochastic ADMM (ICML 2014)
[10.12.2013]Preprint new arXiv version of Positive definite matrices and the symmetric Stein divergence
[04.12.2013]Preprint arXiv version of S. Sra, R. Hosseini, "Conic geometric optimisation on the manifold of positive definite matrices"
[19.11.2013]Preprint arXiv version of S. Jegelka, F. Bach, S. Sra, "Reflection methods for submodular optimization"
[25.10.2013]Paper in IMA J. Numerical Analysis Correlation matrix nearness and completion under observation uncertainty
[05.09.2013]Serving as an Area Chair for ICML 2014
[05.09.2013]Serving on the Senior PC for AISTATS 2014
[04.09.2013]Paper (with S. Jegelka, F. Bach) Reflection methods for submodular optimization
[04.09.2013]Paper (with R. Hosseini) Geometric optimisation for positive definite matrices
[01.09.2013]Visiting ML Dept., School of CS, Carnegie Mellon University for 2 semesters!
[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]Talk: Presented a short version of my new distance function at the NIPS Workshop on "Algebraic Topology and Machine Learning"
[01.12.2012]Paper Similarity computations on positive definite matrices for fast nearest neighbor search. IEEE TPAMI
[07.09.2012]Paper The multivariate Watson distribution: Maximum likelihood and other aspects" in J. Multivariate Analysis
[03.09.2012]Paper Large-scale nonconvex nonsmooth optimization
[03.09.2012]Paper A new distance metric on the manifold of positive definite matrices
[24.06.2012]Talk Speaking @ the NIMS Hot Topics Workshop on Positive Matrices and Operators at KNU, Daegu, Korea
Jun 2013Award. My work on Metric Nearness was selected to receive the SIAM Outstanding Paper Prize, 2011
2012Book 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