Suvrit Sra
Photo credit: Misha Sra
Esther and Harold E. Edgerton (1927) Career Development Associate Professor of EECS.

Core member: Institute for Data, Systems, and Society (IDSS), and of Laboratory for Inf. & Decision Systems (LIDS), Massachusetts Institute of Technology (MIT). I'm a member of the ML Group , the Center for Statistics, and the TILOS (AI Research Institute); and Co-founder, Chief Scientist Pendulum

Contact Info
77 Massachusetts Ave, 32-D662, Massachusetts Institute of Technology, Cambridge, MA 02139
Work:  suvrit at mit     617-253-3816

Social Media

I'm no longer active on social media
(In the past I was active on these sites)
    profile for suvrit at MathOverflow, Q&A for professional mathematicians

Currently away (on leave) at TU Munich

(if you're looking for an intern, PhD, Postdoc, or Researcher position: I'm looking to hire several new team members at TU Munich; not at MIT)

/* I work in machine learning, optimization, and math -- where I care about fundamental theoretical and algorithmic questions as well as applications. The focus of my research is mathematics of AI. A main component of my work is optimization for ML, especially non-convex optimization (eg, how to train Transformers better!), including non-Euclidean and geometric optimization. Other key topics of interest to me: discrete probability, theory of deep learning, theory of sampling, convex geometry, polynomials, combinatorics, etc. [Click here for more!]. */

I am very interested in applications of machine learning to operations research (supply chains), LLM based OPT+ML applications, and more.

[arXiv profile]  [Google Scholar] [Publications]  [Short CV]


NEWS (stale!)

🏆🏆 Nov 2021. I was honored with the Alexander von Humboldt Professorship for AI. A huge thanks to my students, co-authors, mentors, colleagues, and friends, who are the true force behind this honor.
📕 Jikai Jin, Suvrit Sra."Understanding Riemannian Acceleration via a Proximal Extragradient Framework" accepted to COLT 2022.
📕 Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie."Rethinking Convergence in Deep Learning: Beyond Stationary Points" accepted to ICML 2022.
📕 Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie."Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity" accepted to ICML 2022.
📕 Kwangjun Ahn, Jinghzao Zhang, Suvrit Sra."Understanding the unstable convergence of gradient descent" accepted to ICML 2022.
📕 Melanie Weber, Suvrit Sra."Riemannian optimization via Frank-Wolfe Methods". Accepted to appear Mathematical Programming. May 2022.
  Preprint. Xiang Cheng, Jingzhao Zhang, Suvrit Sra. "Theory and Algorithms for Diffusion Processes on Riemannian Manifolds." 2022/4/28.
  Preprint. Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra. Understanding the unstable convergence of gradient descent. 2022/4/3.
  Preprint. Derek Lim, Joshua Robinson, Lingxiao Zhao, Tess Smidt, Suvrit Sra, Haggai Maron, Stefanie Jegelka. "Sign and Basis Invariant Networks for Spectral Graph Representation Learning." 2022/2/25.
  Preprint. Peiyuan Zhang, Jingzhao Zhang, Suvrit Sra. "Minimax in Geodesic Metric Spaces: Sion's Theorem and Algorithms." 2022/2/13.
  Preprint.. Jikai Jin, Suvrit Sra. "A Riemannian Accelerated Proximal Extragradient Framework and its Implications." Feb 2022.
📕 Ali Jadbabaie, Horia Mania, Devavrat Shah, Suvrit Sra. "Time varying regression with hidden linear 2022 dynamics." Accepted to appear in 4th Annual Learning for Dynamics & Control Conference (L4DC), 2022.
  Preprint. Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie. "On Convergence of Training Loss Without Reaching Stationary Points." Feb 2022.
  Preprint. Suvrit Sra. "Positive definite functions of noncommuting contractions, Hua-Bellman matrices, and a new distance metric". 2021/11/30.
  Preprint. Pourya Habib Zadeh, Suvrit Sra. "Introducing Discrepancy Values of Matrices with Application to Bounding Norms of Commutators." 2021/11/23.
Nov 12-2021. 🎤  BLISS seminar UC Berkeley. Title: Some surprising gaps between optimization theory and ML November practice. 2021
Nov 2021. 🎤  Data Science Seminar, London School of Economics. Title: Do we understand how to find critical points in nonsmooth optimization?
Sep 15 2021. 🎤  Keynote speaker 2nd Workshop on Nonsmooth Optimization and its Applications. (Urmia University of Technnology, Iran.
May 2021. 🎤  Keynote speaker: AI for Public Health Workshop at ICLR 2021
Mar 2021. 🎤  FODSI Seminar Series (UC Berkeley). Title: SGD without replacement: optimal rate analysis and more
Mar 2021. 🎤  Boston University, Math-Physics Seminar. Title: Accelerated gradient methods on Riemannian manifolds
Feb 2021. 🎤  Caltech ECE Department Systems Seminar. Title: Accelerated Gradient Methods on Riemannian Manifolds
  Horia Mania and Suvrit Sra. "Why do classifier accuracies show linear trends under distribution shift? 2021
📕 Kwangjun Ahn, Suvrit Sra."Understanding Nesterov's Acceleration via Proximal Point Method." 2022 Symposium on Simplicity in Algorithms (SOSA). SIAM. 2022. pp.117-130
📕 Anshul Shah, Suvrit Sra, Rama Chellappa, Anoop Cherian. "Max-Margin Contrastive Learning."Accepted to appear in AAAI Conference Proceedings. 2022.
📕 Chulhee Yun, Shashank Rajput, Suvrit Sra."Minibatch vs local SGD with shuffling: Tight convergence 2022 bounds and beyond."International Conference on Learning Representations. 2022.
📕 Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, and Suvrit Sra.“Coping with Label Shift via Distributionally Robust Optimisation”. In International Conference on Learning Representations (ICLR), 2021
📕 Alp Yurtsever, Varun Mangalick, Suvrit Sra."Three Operator Splitting with a Nonconvex Loss Function." Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021
📕 Yi Tian, Yuanhao Wang, Tiancheng Yu, Suvrit Sra."Provably Efficient Online Agnostic Learning in Markov Games"Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021
📕 Chulhee Yun, Suvrit Sra, Ali Jadbabaie. "Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?" Conference on Learning Theory (COLT). Proceedings of Machine Learning Research vol 134:1–6, 2021
📕 Alp Yurtsever, Alex Gu, Suvrit Sra. "Three Operator Splitting with Subgradients, Stochastic Gradients, December and Adaptive Learning Rates." Advances in Neural Information Processing Systems (NeurIPS). 2021
📕 Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra. "Can December contrastive learning avoid shortcut solutions?". Advances in Neural Information Processing Systems (NeurIPS), 2021
📕  Suvrit Sra. Metrics Induced by Jensen-Shannon and Related Divergences on Positive Definite Matrices. Linear Algebra and its Applications (LAA)
📕   Projection-free nonconvex stochastic optimization on Riemannian manifolds. IMA Journal of Numerical Analysis. (with Melanie Weber)
Feb 06 2021.   Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? (with Chulhee Yun, Ali Jadbabaie)
Feb 06 2021.   Online Learning in Unknown Markov Games. (with Yi Tian, Yuanhao Wang, Tiancheng Yu)
Feb 06 2021.   Provably Efficient Algorithms for Multi-Objective Competitive RL (with Tiancheng Yu, Yi Tian, Jingzhao Zhang)
Feb 02 2021.   Why do classifier accuracies show linear trends under distribution shift? (with Horia Mania)
📕 Jan 12 2021. Coping with Label Shift via Distributionally Robust Optimisation. (accepted to ICLR 2021 with Jingzhao Zhang, Aditya Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar)
📕 Jan 12 2021. Contrastive Learning with Hard Negative Samples. (accepted to ICLR 2021 with Joshua Robinson, Ching-Yao Chuang, Stefanie Jegelka)

SERVICE

Associate Editor
SIMODS (Dec 2023-)
IMA Inf. & Infer. (Sep 2023-)
JMLR (2018-)
OMS (2014-2020)
2024
Senior Area Chair ICML 2024
Senior Area Chair ICLR 2024
2023
Co-organizer: Simons Inst. Workshop
Senior Area Chair NeuRIPS 2023
2022
Senior Area Chair ICML 2022
Senior Area Chair NeuRIPS 2022
2021
Senior Area Chair ICML 2021
Senior Area Chair NeuRIPS 2021
Senior PC COLT 2021
2020
PC Member Systems & ML
Area Chair AISTATS 2020
Area Chair ICML 2020
Senior PC COLT 2020
Chair OPT 2019
2019
Organizer OPT 2019
Area Chair NeuRIPS 2019
2018
Area Chair NIPS 2018
Area Chair ICML 2018
Sci. Committee: ISMP 2018
Area Chair: COLT 2018
Senior PC: AAAI 2018
2017
Co-chair: OPT2017 Workshop, NIPS 2017 (with A. Agarwal, B. Recht, S. Reddi)
Area Chair: NIPS 2017
PC Member: ICML 2017 Workshop on Principled Approaches to Deep Learning

2020

2020 I'm no longer (resigned) AE for IEEE TPAMI
Dec 18 📕  Metrics Induced by Jensen-Shannon and Related Divergences on Positive Definite Matrices
(accepted to Linear Algebra and its Applications).
Oct   Provably Efficient Online Agnostic Learning in Markov Games
(with Yi Tian, Yuanhao Wang, Tiancheng Yu)
Oct   Coping with Label Shift via Distributionally Robust Optimisation
(with Jingzhao Zhang, Aditya Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar)
Oct   Contrastive learning with hard negative samples
(with Joshua Robinson, Ching-Yao Chuang, Stefanie Jegelka)
Oct 📕  An Interpretable Predictive Model of Vaccine Utilization for Tanzania
(Frontiers of Artificial Intelligence with R. Hariharan, J. Sundberg, G. Gallino, A. Schmidt, D. Arenth, B. Fels).
Sep 📕  Geodesically-convex optimization for averaging partially observed covariance matrices
(ACML 2020 with Florian Yger, Sylvain Chevallier, Quentin Barthélemy).
Sep 📕  SGD with shuffling: optimal rates without component convexity and large epoch requirements
(NeuRIPS 2020 - Spotlight with Kwangjun Ah and Chulhee Yun).
Sep 📕  Towards minimax optimal reinforcement learning in factored markov decision processes
(NeuRIPS 2020 - Spotlight with Yi Tian and Jian Qian)
Sep 📕  Why are Adaptive Methods Good for Attention Models?
(NeuRIPS 2020 with Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank Reddi, Sanjiv Kumar)
June   Stochastic Optimization with Non-stationary Noise
(with Jingzhao Zhang, Hongzhou Lin, Subhro Das, Ali Jadbabaie)
June 📕  Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
(ICML 2020 with Chi Jin, Tiancheng Jin, Haipeng Luo, Tiancheng Yu)
June 📕  Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions
(ICML 2020 with Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Ali Jadbabaie)
June 📕  Strength from Weakness: Fast Learning Using Weak Supervision
(ICML 2020 with Joshua Robinson, Stefanie Jegelka)
May 📕  New concavity and convexity results for symmetric polynomials and their ratios (LMLA)
(Linear and Multilinear Algebra, 68(5), 1031--38)
May 📕  From Nesterov’s Estimate Sequence to Riemannian Acceleration
(COLT 2020 with Kwangjun Ahn)
Apr 18   On Tight Convergence Rates of Without-replacement SGD
(with Kwangjun Ahn).
Mar  Book Chapter: Recent Advances in Stochastic Riemannian Optimization
(in Handbook of Variational Methods... with Reshad Hosseini).
Feb 19   Strength from Weakness: Fast Learning Using Weak Supervision
(with Joshua Robinson, Stefanie Jegelka).
Feb 10   On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions
(with Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Ali Jadbabaie).
Jan 24   From Nesterov's Estimate Sequence to Riemannian Acceleration
(with Kwangjun Ahn).
Jan 07   Learning Adversarial MDPs with Bandit Feedback and Unknown Transition
(with Chi Jin, Tiancheng Jin, Haipeng Luo, and Tiancheng Yu).
Jan 04   Revisiting Hua operator matrices and a new distance on noncommuting contractions

2019

Dec 09   Why ADAM Beats SGD for Attention Models
(with Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank J Reddi, and Sanjiv Kumar)
Dec 06 🎤  ReLU nets are powerful memorizers: a tight analysis of finite sample expressive power  University of Albany, Math Colloquium;   (Abstract)
Nov 22   On upper bounds for permanents of nonnegative matrices
Nov 20 🎤  ReLU nets are powerful memorizers: a tight analysis of finite sample expressive power  Yale University
Nov 18 🎤  ReLU nets are powerful memorizers: a tight analysis of finite sample expressive power  Conference on Data Science and Optimization, Fields Institute, Toronto
Nov 08 🎤  ReLU nets are powerful memorizers: a tight analysis of finite sample expressive power  ML Seminar (WNCG), UT Austin, Austin, Texas
Nov 05   Metrics Induced by Quantum Jensen-Shannon-Rényi and Related Divergences
Oct 18 🎤  Some nonconvex optimization problems through a geometric lens.  CMSA Workshop on: Noncommutative Analysis, Computational Complexity, and Quantum Information
Oct 07   Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods
(with Melanie Weber)
Sep 03 📕  Flexible Modeling of Diversity with Strongly Log-Concave Distributions (NeuRIPS 2019)
(with Joshua Robinson, Stefanie Jegelka)
Sep 03 📕  Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity (NeuRIPS 2019)
(with Chulhee Yun, Ali Jadbabaie)
Sep 03 📕  Are deep ResNets provably better than linear predictors? (NeuRIPS 2019)
(with Chulhee Yun, Ali Jadbabaie)
Jul 22 🎤  Negative dependence, stable polynomials, and all that
ETH Foundations of Data Science Seminar
Jul 19 📕  Acceleration in First Order Quasi-strongly Convex Optimization by ODE Discretization (CDC 2019)
(with Jingzhao Zhang, Ali Jadbabaie)
Jul 09 🎤  Non-convex optimization through a geometric lens
ETH Foundations of Data Science Seminar
May 28   Analysis of Gradient Clipping and Adaptive Scaling with a Relaxed Smoothness Condition
(with Jingzhao Zhang, Ali Jadbabaie)
Apr 24   Zelda Mariet successfully defends her PhD! Congrats!
Apr 21 📕  Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator (ICML 2019)
(with Alp Yurtsever, Volkan Cevher)
Apr 21 📕  Random Shuffling Beats SGD after Finite Epochs (ICML 2019)
(with Jeffery Z. HaoChen)
Apr 21 📕  Escaping Saddle Points with Adaptive Gradient Methods (ICML 2019)
(with Matthew Staib, Sashank Reddi, Satyen Kale, Sanjiv Kumar)
Apr 21   Deep-RBF Networks Revisited: Robust Classification with Rejection
(with Pourya Habib Zadeh, Reshad Hosseini)
Feb 18 📕  An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization (Accepted to Mathematical Programming, Series A, 2019.) (with Reshad Hosseini)
Jan 28   Escaping Saddle Points with Adaptive Gradient Methods
(with Matt Staib, Sashank Reddi, Satyen Kale, Sanjiv Kumar).
Jan 23   Chengtao Li successfully defends his PhD! Congrats!
Jan 08   Hongyi Zhang successfully defends his PhD! Congrats!
Dec 22, '18 📕  Learning Determinantal Point Processes by Sampling Inferred Negatives (AISTATS 2019)
(with Zelda Mariet, Mike Gartrell)
Dec 20, '18 📕  Efficiently testing local optimality and escaping saddles for ReLU networks (ICLR 2019)
(with Chulhee Yun, Ali Jadbabaie)
Decem 20, '18 📕  Small nonlinearities in activation functions create bad local minima in neural networks (ICLR 2019)
(with Chulhee Yun, Ali Jadbabaie)

2018

Dec 22 📕  Learning Determinantal Point Processes by Sampling Inferred Negatives (AISTATS 2019)
(with Zelda Mariet, Mike Gartrell)
Dec 20 📕  Efficiently testing local optimality and escaping saddles for ReLU networks (ICLR 2019)
(with Chulhee Yun, Ali Jadbabaie)
Dec 20 📕  Small nonlinearities in activation functions create bad local minima in neural networks (ICLR 2019)
(with Chulhee Yun, Ali Jadbabaie)
Dec 11   Deep-RBF Networks Revisited: Robust Classification with Rejection
(with Pourya Habib Zadeh, Reshad Hosseini).
Dec 03   Tutorial: Neural information Processing Systems, Conference, Montreal, Canada. (Negative Dependence, Stable Polynomials etc. in Machine Learning with Stefanie Jegelka). [Tutorial materials]
Nov 12   R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate
(with Jingzhao Zhang, Hongyi Zhang).
Nov 08 📕  Modular proximal optimization with application to total variation regularization. JMLR (with Álvaro Barbero.)
Dec '18 📕  Exponentiated Strongly Rayleigh Measures. (NIPS 2018)
(with Zelda Mariet, Stefanie Jegelka)
Dec '18 📕  Direct Runge-Kutta Discretization Achieves Acceleration (NIPS 2018)
(with Jingzhao Zhang, Aryan Mokhtari, Ali Jadbabaie)
Oct '18   Efficiently testing local optimality and escaping saddles for ReLU networks
(with Chulhee Yun, Ali Jadbabaie)
Oct '18   Finite sample expressive power of small-width ReLU networks
(with Chulhee Yun, Ali Jadbabaie)
Oct 09 🎤  A critical view of optimality in deep learning
BU Algorithms and Theory seminar
Sep 03 📕  New concavity and convexity results for symmetric polynomials and their ratios (LMLA)
(to appear in Linear and Multilinear Algebra)
Aug 13 🎤  Geometric nonconvex optimization
At the DIMACS/TRIPODS/MOPTA 2018 joint conference and workshop
Jul 31 🎤  Tractable nonconvex optimization via geometry
At the IFDS TRIPODS workshop on non-convex optimization
Jun 26   Random Shuffling Beats SGD after Finite Epochs
(with Jeffrey Z. HaoChen)
Jun 02 📕  On Geodesically Convex Formulations for the Brascamp-Lieb Constant (APPROX 2018)
(with Nisheeth K. Vishnoi and Ozan Yıldız)
May 01 📕  An Estimate Sequence for Geodesically Convex Optimization (COLT 2018)
(with Hongyi Zhang)
May 01   Direct Runge-Kutta Discretization Achieves Acceleration
(with Jingzhao Zhang, Aryan Mokhtari, Ali Jadbabaie)
Apr '18   CONGRATS to Zelda for winning a 2018 Google Research Fellowship!
Mar 26   New concavity and convexity results for symmetric polynomials and their ratios
Mar 25 📕  Non-Linear Temporal Subspace Representations for Activity Recognition (CVPR 2018)
(with Anoop Cherian, Stephen Gould, Richard Hartley)
Feb 06   Learning Determinantal Point Processes by Sampling Inferred Negatives
(with Zelda Mariet, Mike Gartrell)
Feb 06   A critical view of global optimality in deep learning
(with Chulhee Yun, Ali Jadbabaie)

2017

Dec 22 📕  A Generic Approach for Escaping Saddle points
(with S. Reddi, M. Zaheer. B. Poczos, F. Bach, R. Salakhutdinov, A. Smola; accepted to AISTATS 2018)
Dec 14 🎤  EECS Special Seminar, MIT
Nov/Dec 🎤  Simons Institute, UC Berkeley, Workshop on Optimization, Statistics, and Uncertainty.
Oct 05 🎤  Trends in large-scale nonconvex optimization.
Simons Institute, UC Berkeley, Workshop on Fast Iterative Methods in Optimization
9/19/17 Awarded NSF BIGDATA grant on Interpretable, interactive, and scalable learning via discrete probability;
(joint project with Stefanie Jegelka)
Fall' 17   Teaching: 6.867 Machine Learning
(EECS graduate course), (with Devavrat Shah, David Sontag)
Oct 29   Modular proximal optimization with application to total variation regularization
(with Álvaro Barbero; overhauled version.)
Oct 29   On the computation of Wasserstein barycenters of multivariate Gaussians
Oct 29   Frank-Wolfe methods for geodesically convex optimization
(with Melanie Weber)
Sep 25 📕  Logarithmic inequalities under an elementary symmetric polynomial dominance order
(accepted with minor revision to Proceedings American Math. Society (PAMS), )
Sep 05   A Generic Approach for Escaping Saddle points
(with S. Reddi, M. Zaheer. B. Poczos, F. Bach, R. Salakhutdinov, A. Smola)
Sep 05 📕  Column Subset Selection via Polynomial Time Dual Volume Sampling
(with Chengtao Li, Stefanie Jegelka; Advances in Neural Information Processing Systems (NIPS) 2017)
Sep 05 📕  Elementary Symmetric Polynomials for Optimal Experimental Design
(with Zelda Mariet; Advances in Neural Information Processing Systems (NIPS) 2017)
Jul 10   Lecturing: Optimization for Machine Learning: Convex and Nonconvex.
(At Beijing International Center for Mathematical Research (BICMR); Peking University;
Applied Math Summer School). [1-3]; [4-5]; [6]; [7]; [8]; [9]; [10]
Jul '17   Unsupervised robust nonparametric learning of hidden community properties
(with Mikhail A. Langovoy, Akhilesh Gotmare, and Martin Jaggi)
Jul 06   Global optimality conditions for deep neural networks.
(with Chulhee Yun, Ali Jadbabaie)
Jun 29   Distributional Adversarial Networks
(with Chengtao Li, David Alvarez-Melis, Keyulu Xu, Stefanie Jegelka); [Code Repo]
Jun 12   An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization
(with Reshad Hosseini)
Jun '17   Lecturing: Optimization for Machine Learning (Machine Learning Summer School, MLSS).
(At Max Planck Institute for Intelligent Systems, Tübingen, Germany)
[Lect 1],    [Lect 2],    [Lect 3A],    [Lect 3B].
May 25   Received a Criteo faculty research award. (Thanks Criteo!)
May 24   Elementary Symmetric Polynomials for Optimal Experimental Design
(with Zelda Mariet)
May 24   Sequence Summarization Using Order-constrained Kernelized Feature Subspaces
(with Anoop Cherian, Richard Hartley)
May 12 🎤  Bayopt 2017. (Conference in honor of Roger J-B Wets on his 80th birthday)
Apr-May   Visiting: Foundations of Machine Learning as a long-term participant.
(Simons Institute, UC Berkeley, CA)
Apr 24 🎤  Geometric optimization: convex and nonconvex.
(BLISS Seminar, UC Berkeley Information Systems and Sciences)
Apr 11 🎤  Optimization and Statistical Learning (OSL' 17)
Mar 25   Markov Chains for Cardinality Restricted Strongly Rayleigh Measures via Chain Combination
(with Chengtao Li, Stefanie Jegelka)
Mar 08   Column Subset Selection via Polynomial Time Dual Volume Sampling
(with Chengtao Li, Stefanie Jegelka)
Jan '17   Visiting: Foundations of Machine Learning as a long-term participant.
(Simons Institute, UC Berkeley, CA)
Jan 24 📕  Combinatorial Topic Models using Small–Variance Asymptotics
(with Ke Jiang, Brian Kulis; Artificial Intelligence and Statistics (AISTATS) 2017)

2016

Dec 10 🎤  Workshop: OPT2016: Optimization for Machine Learning
(the 9th OPTML workshop at NIPS; co-organized with Francis Bach, Niao He, and Sashank Reddi)
Dec 09 🎤  At the Nonconvex Optimization for Machine Learning: Theory and Practice Workshop
(a NIPS 2016 workshop; speaking on Taming nonconvexity via geometry)
Dec 05   Tutorial: Neural Information Processing Systems (NIPS), Conference, Barcelona, Spain
(Large-Scale Optimization: Beyond Stochastic Gradient Descent and Convexity with Francis Bach)
[slides part 1], [slides part 2]
Nov 04 🎤  Data Science Seminar, Northeastern University, Boston.
(on Geometric Optimization)
Sep 13 🎤  LIDS Seminar, MIT
(in the LIDS Seminar series, on the topic of Geometric Optimization)
Fall' 16   Teaching: 6.867 Machine Learning (EECS graduate course)
(with Leslie Kaelbling, Tomas Lozano-Perez)
Aug 12 📕  Markov Chain Sampling in Discrete Probabilistic Models with Constraints
(with Chengtao Li, Stefanie Jegelka)
Advances in Neural Information Processing Systems (NIPS) 2016
Aug 12 📕  Kronecker Determinantal Point Processes
(with Z. Mariet)
Advances in Neural Information Processing Systems (NIPS) 2016
Aug 12 📕  Fast stochastic optimization on Riemannian manifolds
(with H. Zhang, S. Reddi)
Advances in Neural Information Processing Systems (NIPS) 2016
Aug 12 📕  Fast Stochastic Methods for Nonsmooth Nonconvex Optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola)
Advances in Neural Information Processing Systems (NIPS) 2016
Aug 08 📕  Stochastic Frank-Wolfe Methods for Nonconvex Optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola)
54th Allerton Conference on on Communication, Control, and Computing, 2016.
Aug 08 🎤  OPT 2016: Optimization for Machine Learning accepted to NIPS.
The 9th NIPS Workshop on Optimization of Machine Learning; stay tuned for updates.
(co-organized with Francis Bach, Sashank Reddi, Niao He)
Aug 02   Markov Chain Sampling in Discrete Probabilistic Models with Constraints
(with Chengtao Li, Stefanie Jegelka)
Aug 02 📕  Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices
(with Anoop Cherian)
to appear in IEEE TNNLS
Jul 24 📕  Fast incremental method for smooth nonconvex optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola).
to appear in IEEE Conference on Decision and Control (CDC) 2016.
Jul 14   Stochastic Frank-Wolfe Methods for Nonconvex Optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola)
Jul 13   Fast sampling for Strongly Rayleigh Measures with Application to Determinantal Point Processes
(with Chengtao Li, Stefanie Jegelka)
Jul 11 🎤  At SIAM Annual Meeting 2016, Boston.
Organizing Advances in large-scale optimization.
Jun 23   Speaking at the Nonconvex Optimization Workshop
(on Fast Nonconvex Stochastic Optimization)
Jun 20 🎤  At ICML 2016, NYC. See the papers below!
May 20   Kronecker Determinantal Point Processes
(with Z. Mariet)
May 20   Fast stochastic optimization on Riemannian manifolds
(with H. Zhang, S. Reddi)
May 20   Fast Stochastic Methods for Nonsmooth Nonconvex Optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola)
May 05 📕  On the Matrix Square Root via Geometric Optimization
Accepted to Electronic Journal on Linear Algebra (ELA)
Apr 26 📕  First-order methods for geodesically convex optimization
(with Hongyi Zhang). Conference on Learning Theory (COLT 2016)
Apr 24 📕  Geometric Mean Metric Learning
(with Pourya H. Zadeh, Reshad Hosseini)
International Conference on Machine Learning (ICML 2016)
Apr 24 📕  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 📕  Stochastic variance reduction for nonconvex optimization
(with Sashank Reddi, Ahmed Hefny, Barnabas Poczos, Alexander Smola).
International Conference on Machine Learning (ICML 2016)
Apr 24 📕  Gaussian quadrature for matrix inverse forms with applications
(with Chengtao Li, Stefanie Jegelka).
International Conference on Machine Learning (ICML 2016)
Apr 24 📕  Fast DPP sampling for Nyström with application to Kernel Methods
(with Chengtao Li, Stefanie Jegelka).
International Conference on Machine Learning (ICML 2016)
Apr 21 📕  Entropic Metric Alignment for Correspondence Problems
(with Justin Solomon, Gabriel Peyré, Vladimir Kim).
Accepted to ACM SIGGRAPH 2016
Apr 07   Combinatorial Topic Models using Small–Variance Asymptotics
(with Ke Jiang, Brian Kulis)
Mar 18   Fast DPP sampling for Nyström with application to Kernel Methods
(with Chengtao Li, Stefanie Jegelka)
Mar 13   Fast incremental method for smooth nonconvex optimization
(with Sashank Reddi, Barnabas Poczos, Alex Smola) [arXiv]
Feb 21   First-order methods for geodesically convex optimization
(with Hongyi Zhang)
Feb 14 📕  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   Stochastic variance reduction for nonconvex optimization
(with Sashank Reddi, Ahmed Hefny, Barnabas Poczos, Alexander Smola). [arXiv]
Feb 02 📕  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 📕  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📕  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📕  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  (update) Riemannian dictionary learning and sparse coding
(with A. Cherian)
Dec 17  (update) Inference and mixture modeling with the Elliptical Gamma distribution
(with Reshad Hosseini, Lucas Theis, Matthias Bethge)
Dec 16  (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  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  Diversity Networks
(with Zelda Mariet)
Sep 18  Inequalities via elementary symmetric polynomial monotonicity
Sep 07  Efficient structured low rank minimization
(with Adams Wei Yu, Wanli Ma, Yaoliang Yu)
Sep 07  Efficient Sampling for K-Determinantal Point Processes
(with Chengtao Li, Stefanie Jegelka)
Sep 07📕  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📕  on Manifold optimization for mixture models
accepted to NIPS 2015 (with R. Hosseini)
Sep 04📕  Asynchronous variance reduced stochastic gradient
accepted to NIPS 2015 (with with Sashank Reddi, Ahmed Hefny, Barnabas Poczos, Alexander Smola)
Aug 20  on Delay sensitive distributed optimization
(with Adams Wei Yu, Mu Li, Alexander Smola)
Aug 17  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  Matrix square roots via geometric optimization
Jul 13  Conic geometric optimisation at ISMP, 2015
Jul 10  Riemannian dictionary learning and sparse coding
(with Anoop Cherian)
Jun 24 Preprint Manifold optimization for mixture models
(with Reshad Hosseini)
Jun 24📕  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📕  Inequalities for normalized Schur functions
accepted to European Journal of Combinatorics (my first combinatorics paper!)
May 12📕  Operator Hlawka-like inequalities on positive definite tensors
(with Wolfgang Berndt) to Linear Algebra and its Applications (LAA)
May 12📕  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📕  Efficiently learning determinantal point processes
(with Z. Mariet). accepted to ICML'15. written during my first two weeks at MIT!
Apr 04  (new version) Explicit diagonalization of an anti-triangular Cesaró matrix
Mar 13  Speaking about Schur functions at the MIT Combinatorics Seminar!!
Mar 01  Proof of a conjecture in combinatorics: On inequalities for normalized Schur functions
Jan 22📕  Conic geometric optimisation on the manifold of positive definite matrices
(with Reshad Hosseini) accepted for publication to SIAM J. Optimization
Jan 17📕  Data Modeling with the Elliptical Gamma Distribution
upcoming in AISTATS 2015 (with Reshad Hosseini)
Jan 16 Started at MIT!

2014 and older

[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
[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] 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

Copyright © suvrit sra 2015