default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSuvrit Sra
Person information
- affiliation: Massachusetts Institute of Technology (MIT), Laboratory for Information and Decision Systems, Cambridge, MA, USA
- affiliation: Max Planck Institute for Biological Cybernetics, Tübingen, Germany
- affiliation: University of Texas at Austin, Department of Computer Sciences, Austin, TX, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c108]Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra:
Linear attention is (maybe) all you need (to understand Transformer optimization). ICLR 2024- [c107]Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra:
How to Escape Sharp Minima with Random Perturbations. ICML 2024 - [c106]Xiang Cheng, Yuxin Chen, Suvrit Sra:
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context. ICML 2024 - [i83]Xiang Cheng, Jingzhao Zhang, Suvrit Sra:
Efficient Sampling on Riemannian Manifolds via Langevin MCMC. CoRR abs/2402.10357 (2024) - [i82]Sanchayan Dutta, Xiang Cheng, Suvrit Sra:
Riemannian Bilevel Optimization. CoRR abs/2405.15816 (2024) - [i81]Guy Kornowski, Swati Padmanabhan, Kai Wang, Zhe Zhang, Suvrit Sra:
First-Order Methods for Linearly Constrained Bilevel Optimization. CoRR abs/2406.12771 (2024) - [i80]Sanchayan Dutta, Suvrit Sra:
Memory-augmented Transformers can implement Linear First-Order Optimization Methods. CoRR abs/2410.07263 (2024) - [i79]Xiang Cheng, Lawrence Carin, Suvrit Sra:
Graph Transformers Dream of Electric Flow. CoRR abs/2410.16699 (2024) - 2023
- [j20]Melanie Weber
, Suvrit Sra:
Riemannian Optimization via Frank-Wolfe Methods. Math. Program. 199(1): 525-556 (2023) - [j19]Peiyuan Zhang, Jingzhao Zhang, Suvrit Sra:
Sion's Minimax Theorem in Geodesic Metric Spaces and a Riemannian Extragradient Algorithm. SIAM J. Optim. 33(4): 2885-2908 (2023) - [c105]Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra:
Toward Understanding State Representation Learning in MuZero: A Case Study in Linear Quadratic Gaussian Control. CDC 2023: 6166-6171 - [c104]Derek Lim, Joshua David Robinson, Lingxiao Zhao, Tess E. Smidt, Suvrit Sra, Haggai Maron, Stefanie Jegelka:
Sign and Basis Invariant Networks for Spectral Graph Representation Learning. ICLR 2023 - [c103]Melanie Weber, Suvrit Sra:
Global optimality for Euclidean CCCP under Riemannian convexity. ICML 2023: 36790-36803 - [c102]David Xing Wu, Chulhee Yun, Suvrit Sra:
On the Training Instability of Shuffling SGD with Batch Normalization. ICML 2023: 37787-37845 - [c101]Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra:
Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control? L4DC 2023: 51-63 - [c100]Yan Dai, Kwangjun Ahn, Suvrit Sra:
The Crucial Role of Normalization in Sharpness-Aware Minimization. NeurIPS 2023 - [c99]Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand, Suvrit Sra:
Transformers learn to implement preconditioned gradient descent for in-context learning. NeurIPS 2023 - [i78]David Xing Wu, Chulhee Yun, Suvrit Sra:
On the Training Instability of Shuffling SGD with Batch Normalization. CoRR abs/2302.12444 (2023) - [i77]Yan Dai, Kwangjun Ahn, Suvrit Sra:
The Crucial Role of Normalization in Sharpness-Aware Minimization. CoRR abs/2305.15287 (2023) - [i76]Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra:
How to escape sharp minima. CoRR abs/2305.15659 (2023) - [i75]Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand, Suvrit Sra:
Transformers learn to implement preconditioned gradient descent for in-context learning. CoRR abs/2306.00297 (2023) - [i74]Adarsh Barik, Suvrit Sra, Jean Honorio:
Invex Programs: First Order Algorithms and Their Convergence. CoRR abs/2307.04456 (2023) - [i73]Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra:
Linear attention is (maybe) all you need (to understand transformer optimization). CoRR abs/2310.01082 (2023) - [i72]Xiang Cheng, Yuxin Chen, Suvrit Sra:
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context. CoRR abs/2312.06528 (2023) - 2022
- [c98]Anshul Shah, Suvrit Sra, Rama Chellappa, Anoop Cherian:
Max-Margin Contrastive Learning. AAAI 2022: 8220-8230 - [c97]Jikai Jin, Suvrit Sra:
Understanding Riemannian Acceleration via a Proximal Extragradient Framework. COLT 2022: 2924-2962 - [c96]Chulhee Yun, Shashank Rajput, Suvrit Sra:
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. ICLR 2022 - [c95]Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra:
Understanding the unstable convergence of gradient descent. ICML 2022: 247-257 - [c94]Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie:
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective. ICML 2022: 26330-26346 - [c93]Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie:
Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity. ICML 2022: 26347-26361 - [c92]Horia Mania, Ali Jadbabaie, Devavrat Shah, Suvrit Sra:
Time Varying Regression with Hidden Linear Dynamics. L4DC 2022: 858-869 - [c91]Xiang Cheng, Jingzhao Zhang, Suvrit Sra:
Efficient Sampling on Riemannian Manifolds via Langevin MCMC. NeurIPS 2022 - [c90]Alp Yurtsever, Suvrit Sra:
CCCP is Frank-Wolfe in disguise. NeurIPS 2022 - [c89]Kwangjun Ahn, Suvrit Sra:
Understanding Nesterov's Acceleration via Proximal Point Method. SOSA 2022: 117-130 - [i71]Peiyuan Zhang, Jingzhao Zhang, Suvrit Sra:
Minimax in Geodesic Metric Spaces: Sion's Theorem and Algorithms. CoRR abs/2202.06950 (2022) - [i70]Derek Lim, Joshua Robinson, Lingxiao Zhao, Tess E. Smidt, Suvrit Sra, Haggai Maron, Stefanie Jegelka:
Sign and Basis Invariant Networks for Spectral Graph Representation Learning. CoRR abs/2202.13013 (2022) - [i69]Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra:
Understanding the unstable convergence of gradient descent. CoRR abs/2204.01050 (2022) - [i68]Suvrit Sra, Melanie Weber:
On a class of geodesically convex optimization problems solved via Euclidean MM methods. CoRR abs/2206.11426 (2022) - [i67]Melanie Weber, Suvrit Sra:
Computing Brascamp-Lieb Constants through the lens of Thompson Geometry. CoRR abs/2208.05013 (2022) - [i66]Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra:
Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control? CoRR abs/2212.14511 (2022) - 2021
- [c88]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? COLT 2021: 4653-4658 - [c87]Joshua David Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka:
Contrastive Learning with Hard Negative Samples. ICLR 2021 - [c86]Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra:
Coping with Label Shift via Distributionally Robust Optimisation. ICLR 2021 - [c85]Yi Tian, Yuanhao Wang, Tiancheng Yu, Suvrit Sra:
Online Learning in Unknown Markov Games. ICML 2021: 10279-10288 - [c84]Tiancheng Yu, Yi Tian, Jingzhao Zhang, Suvrit Sra:
Provably Efficient Algorithms for Multi-Objective Competitive RL. ICML 2021: 12167-12176 - [c83]Alp Yurtsever, Varun Mangalick, Suvrit Sra:
Three Operator Splitting with a Nonconvex Loss Function. ICML 2021: 12267-12277 - [c82]Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra:
Can contrastive learning avoid shortcut solutions? NeurIPS 2021: 4974-4986 - [c81]Alp Yurtsever, Alex Gu, Suvrit Sra:
Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates. NeurIPS 2021: 19743-19756 - [i65]Tiancheng Yu, Yi Tian, Jingzhao Zhang, Suvrit Sra:
Provably Efficient Algorithms for Multi-Objective Competitive RL. CoRR abs/2102.03192 (2021) - [i64]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? CoRR abs/2103.07079 (2021) - [i63]Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra:
Can contrastive learning avoid shortcut solutions? CoRR abs/2106.11230 (2021) - [i62]Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie:
On Convergence of Training Loss Without Reaching Stationary Points. CoRR abs/2110.06256 (2021) - [i61]Chulhee Yun, Shashank Rajput, Suvrit Sra:
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. CoRR abs/2110.10342 (2021) - [i60]Jikai Jin, Suvrit Sra:
A Riemannian Accelerated Proximal Extragradient Framework and its Implications. CoRR abs/2111.02763 (2021) - [i59]Anshul Shah, Suvrit Sra, Rama Chellappa, Anoop Cherian:
Max-Margin Contrastive Learning. CoRR abs/2112.11450 (2021) - 2020
- [j18]Ramkumar Hariharan, Johnna Sundberg, Giacomo Gallino, Ashley Schmidt, Drew Arenth, Suvrit Sra, Benjamin Fels:
An Interpretable Predictive Model of Vaccine Utilization for Tanzania. Frontiers Artif. Intell. 3: 559617 (2020) - [j17]Reshad Hosseini, Suvrit Sra:
An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization. Math. Program. 181(1): 187-223 (2020) - [c80]Florian Yger, Sylvain Chevallier, Quentin Barthélemy, Suvrit Sra:
Geodesically-convex optimization for averaging partially observed covariance matrices. ACML 2020: 417-432 - [c79]Kwangjun Ahn, Suvrit Sra:
From Nesterov's Estimate Sequence to Riemannian Acceleration. COLT 2020: 84-118 - [c78]Jingzhao Zhang, Tianxing He, Suvrit Sra, Ali Jadbabaie:
Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity. ICLR 2020 - [c77]Chi Jin, Tiancheng Jin, Haipeng Luo, Suvrit Sra, Tiancheng Yu:
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition. ICML 2020: 4860-4869 - [c76]Joshua Robinson, Stefanie Jegelka, Suvrit Sra:
Strength from Weakness: Fast Learning Using Weak Supervision. ICML 2020: 8127-8136 - [c75]Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Suvrit Sra, Ali Jadbabaie:
Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions. ICML 2020: 11173-11182 - [c74]Kwangjun Ahn, Chulhee Yun, Suvrit Sra:
SGD with shuffling: optimal rates without component convexity and large epoch requirements. NeurIPS 2020 - [c73]Yi Tian, Jian Qian, Suvrit Sra:
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes. NeurIPS 2020 - [c72]Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank J. Reddi, Sanjiv Kumar, Suvrit Sra:
Why are Adaptive Methods Good for Attention Models? NeurIPS 2020 - [i58]Jingzhao Zhang, Hongzhou Lin, Suvrit Sra, Ali Jadbabaie:
On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions. CoRR abs/2002.04130 (2020) - [i57]Joshua Robinson, Stefanie Jegelka, Suvrit Sra:
Strength from Weakness: Fast Learning Using Weak Supervision. CoRR abs/2002.08483 (2020) - [i56]Kwangjun Ahn, Suvrit Sra:
On Tight Convergence Rates of Without-replacement SGD. CoRR abs/2004.08657 (2020) - [i55]Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie:
Stochastic Optimization with Non-stationary Noise. CoRR abs/2006.04429 (2020) - [i54]Yi Tian, Jian Qian, Suvrit Sra:
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes. CoRR abs/2006.13405 (2020) - [i53]Joshua Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka:
Contrastive Learning with Hard Negative Samples. CoRR abs/2010.04592 (2020) - [i52]Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra:
Coping with Label Shift via Distributionally Robust Optimisation. CoRR abs/2010.12230 (2020) - [i51]Yi Tian, Yuanhao Wang, Tiancheng Yu, Suvrit Sra:
Provably Efficient Online Agnostic Learning in Markov Games. CoRR abs/2010.15020 (2020) - [i50]Horia Mania, Suvrit Sra:
Why do classifier accuracies show linear trends under distribution shift? CoRR abs/2012.15483 (2020)
2010 – 2019
- 2019
- [c71]Zelda Mariet, Mike Gartrell, Suvrit Sra:
Learning Determinantal Point Processes by Corrective Negative Sampling. AISTATS 2019: 2251-2260 - [c70]Jingzhao Zhang, Suvrit Sra, Ali Jadbabaie:
Acceleration in First Order Quasi-strongly Convex Optimization by ODE Discretization. CDC 2019: 1501-1506 - [c69]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Efficiently testing local optimality and escaping saddles for ReLU networks. ICLR (Poster) 2019 - [c68]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Small nonlinearities in activation functions create bad local minima in neural networks. ICLR (Poster) 2019 - [c67]Jeff Z. HaoChen, Suvrit Sra:
Random Shuffling Beats SGD after Finite Epochs. ICML 2019: 2624-2633 - [c66]Matthew Staib, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar, Suvrit Sra:
Escaping Saddle Points with Adaptive Gradient Methods. ICML 2019: 5956-5965 - [c65]Alp Yurtsever, Suvrit Sra, Volkan Cevher:
Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator. ICML 2019: 7282-7291 - [c64]Joshua Robinson, Suvrit Sra, Stefanie Jegelka:
Flexible Modeling of Diversity with Strongly Log-Concave Distributions. NeurIPS 2019: 15199-15209 - [c63]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity. NeurIPS 2019: 15532-15543 - [c62]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Are deep ResNets provably better than linear predictors? NeurIPS 2019: 15660-15669 - [i49]Matthew Staib, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar, Suvrit Sra:
Escaping Saddle Points with Adaptive Gradient Methods. CoRR abs/1901.09149 (2019) - [i48]Jingzhao Zhang, Tianxing He, Suvrit Sra, Ali Jadbabaie:
Analysis of Gradient Clipping and Adaptive Scaling with a Relaxed Smoothness Condition. CoRR abs/1905.11881 (2019) - [i47]Joshua Robinson, Suvrit Sra, Stefanie Jegelka:
Flexible Modeling of Diversity with Strongly Log-Concave Distributions. CoRR abs/1906.05413 (2019) - [i46]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Are deep ResNets provably better than linear predictors? CoRR abs/1907.03922 (2019) - [i45]Melanie Weber, Suvrit Sra:
Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods. CoRR abs/1910.04194 (2019) - [i44]Suvrit Sra:
Metrics Induced by Quantum Jensen-Shannon-Renyí and Related Divergences. CoRR abs/1911.02643 (2019) - [i43]Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank J. Reddi, Sanjiv Kumar, Suvrit Sra:
Why ADAM Beats SGD for Attention Models. CoRR abs/1912.03194 (2019) - 2018
- [j16]Álvaro Barbero Jiménez, Suvrit Sra:
Modular Proximal Optimization for Multidimensional Total-Variation Regularization. J. Mach. Learn. Res. 19: 56:1-56:82 (2018) - [c61]Sashank J. Reddi, Manzil Zaheer, Suvrit Sra, Barnabás Póczos, Francis R. Bach, Ruslan Salakhutdinov, Alexander J. Smola:
A Generic Approach for Escaping Saddle points. AISTATS 2018: 1233-1242 - [c60]Suvrit Sra, Nisheeth K. Vishnoi, Ozan Yildiz:
On Geodesically Convex Formulations for the Brascamp-Lieb Constant. APPROX-RANDOM 2018: 25:1-25:15 - [c59]Hongyi Zhang, Suvrit Sra:
An Estimate Sequence for Geodesically Convex Optimization. COLT 2018: 1703-1723 - [c58]Anoop Cherian, Suvrit Sra, Stephen Gould, Richard Hartley:
Non-Linear Temporal Subspace Representations for Activity Recognition. CVPR 2018: 2197-2206 - [c57]Chengtao Li, David Alvarez-Melis, Keyulu Xu, Stefanie Jegelka, Suvrit Sra:
Distributional Adversarial Networks. ICLR (Workshop) 2018 - [c56]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Global Optimality Conditions for Deep Neural Networks. ICLR (Poster) 2018 - [c55]Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie:
Direct Runge-Kutta Discretization Achieves Acceleration. NeurIPS 2018: 3904-3913 - [c54]Zelda E. Mariet, Suvrit Sra, Stefanie Jegelka:
Exponentiated Strongly Rayleigh Distributions. NeurIPS 2018: 4464-4474 - [i42]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
A Critical View of Global Optimality in Deep Learning. CoRR abs/1802.03487 (2018) - [i41]Zelda Mariet, Mike Gartrell, Suvrit Sra:
Learning Determinantal Point Processes by Sampling Inferred Negatives. CoRR abs/1802.05649 (2018) - [i40]Anoop Cherian, Suvrit Sra, Stephen Gould, Richard Hartley:
Non-Linear Temporal Subspace Representations for Activity Recognition. CoRR abs/1803.11064 (2018) - [i39]Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie:
Direct Runge-Kutta Discretization Achieves Acceleration. CoRR abs/1805.00521 (2018) - [i38]Hongyi Zhang, Suvrit Sra:
Towards Riemannian Accelerated Gradient Methods. CoRR abs/1806.02812 (2018) - [i37]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Efficiently testing local optimality and escaping saddles for ReLU networks. CoRR abs/1809.10858 (2018) - [i36]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Finite sample expressive power of small-width ReLU networks. CoRR abs/1810.07770 (2018) - [i35]Jingzhao Zhang, Hongyi Zhang, Suvrit Sra:
R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate. CoRR abs/1811.04194 (2018) - [i34]Pourya Habib Zadeh, Reshad Hosseini, Suvrit Sra:
Deep-RBF Networks Revisited: Robust Classification with Rejection. CoRR abs/1812.03190 (2018) - 2017
- [j15]Anoop Cherian, Suvrit Sra:
Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices. IEEE Trans. Neural Networks Learn. Syst. 28(12): 2859-2871 (2017) - [c53]Ke Jiang, Suvrit Sra, Brian Kulis:
Combinatorial Topic Models using Small-Variance Asymptotics. AISTATS 2017: 421-429 - [c52]Zelda E. Mariet, Suvrit Sra:
Elementary Symmetric Polynomials for Optimal Experimental Design. NIPS 2017: 2139-2148 - [c51]Chengtao Li, Stefanie Jegelka, Suvrit Sra:
Polynomial time algorithms for dual volume sampling. NIPS 2017: 5038-5047 - [i33]Anoop Cherian, Suvrit Sra, Richard Hartley:
Sequence Summarization Using Order-constrained Kernelized Feature Subspaces. CoRR abs/1705.08583 (2017) - [i32]Reshad Hosseini, Suvrit Sra:
An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization. CoRR abs/1706.03267 (2017) - [i31]Chengtao Li, David Alvarez-Melis, Keyulu Xu, Stefanie Jegelka, Suvrit Sra:
Distributional Adversarial Networks. CoRR abs/1706.09549 (2017) - [i30]Chulhee Yun, Suvrit Sra, Ali Jadbabaie:
Global optimality conditions for deep neural networks. CoRR abs/1707.02444 (2017) - [i29]Mikhail A. Langovoy, Akhilesh Gotmare, Martin Jaggi, Suvrit Sra:
Unsupervised robust nonparametric learning of hidden community properties. CoRR abs/1707.03494 (2017) - [i28]Sashank J. Reddi, Manzil Zaheer, Suvrit Sra, Barnabás Póczos, Francis R. Bach, Ruslan Salakhutdinov, Alexander J. Smola:
A Generic Approach for Escaping Saddle points. CoRR abs/1709.01434 (2017) - [i27]Melanie Weber, Suvrit Sra:
Frank-Wolfe methods for geodesically convex optimization with application to the matrix geometric mean. CoRR abs/1710.10770 (2017) - 2016
- [j14]Reshad Hosseini, Suvrit Sra, Lucas Theis, Matthias Bethge:
Inference and mixture modeling with the Elliptical Gamma Distribution. Comput. Stat. Data Anal. 101: 29-43 (2016) - [j13]Suvrit Sra:
On inequalities for normalized Schur functions. Eur. J. Comb. 51: 492-494 (2016) - [j12]Justin Solomon, Gabriel Peyré, Vladimir G. Kim, Suvrit Sra:
Entropic metric alignment for correspondence problems. ACM Trans. Graph. 35(4): 72:1-72:13 (2016) - [c50]Suvrit Sra, Adams Wei Yu, Mu Li, Alexander J. Smola:
AdaDelay: Delay Adaptive Distributed Stochastic Optimization. AISTATS 2016: 957-965 - [c49]Chengtao Li, Stefanie Jegelka, Suvrit Sra:
Efficient Sampling for k-Determinantal Point Processes. AISTATS 2016: 1328-1337 - [c48]Sashank J. Reddi, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Stochastic Frank-Wolfe methods for nonconvex optimization. Allerton 2016: 1244-1251 - [c47]Sashank J. Reddi, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Fast incremental method for smooth nonconvex optimization. CDC 2016: 1971-1977 - [c46]Hongyi Zhang, Suvrit Sra:
First-order Methods for Geodesically Convex Optimization. COLT 2016: 1617-1638 - [c45]Sashank J. Reddi, Ahmed Hefny, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Stochastic Variance Reduction for Nonconvex Optimization. ICML 2016: 314-323 - [c44]Yu-Xiang Wang, Veeranjaneyulu Sadhanala, Wei Dai, Willie Neiswanger, Suvrit Sra, Eric P. Xing:
Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms. ICML 2016: 1548-1557 - [c43]Chengtao Li, Suvrit Sra, Stefanie Jegelka:
Gaussian quadrature for matrix inverse forms with applications. ICML 2016: 1766-1775 - [c42]Chengtao Li, Stefanie Jegelka, Suvrit Sra:
Fast DPP Sampling for Nystrom with Application to Kernel Methods. ICML 2016: 2061-2070 - [c41]Pourya Zadeh, Reshad Hosseini, Suvrit Sra:
Geometric Mean Metric Learning. ICML 2016: 2464-2471 - [c40]Sashank J. Reddi, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization. NIPS 2016: 1145-1153 - [c39]Zelda E. Mariet, Suvrit Sra:
Kronecker Determinantal Point Processes. NIPS 2016: 2694-2702 - [c38]Chengtao Li, Suvrit Sra, Stefanie Jegelka:
Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling. NIPS 2016: 4188-4196 - [c37]Hongyi Zhang, Sashank J. Reddi, Suvrit Sra:
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds. NIPS 2016: 4592-4600 - [c36]Zelda Mariet, Suvrit Sra:
Diversity Networks. ICLR (Poster) 2016 - [i26]Hongyi Zhang, Suvrit Sra:
First-order Methods for Geodesically Convex Optimization. CoRR abs/1602.06053 (2016) - [i25]Chengtao Li, Stefanie Jegelka, Suvrit Sra:
Fast DPP Sampling for Nyström with Application to Kernel Methods. CoRR abs/1603.06052 (2016) - [i24]Sashank J. Reddi, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Fast Incremental Method for Nonconvex Optimization. CoRR abs/1603.06159 (2016) - [i23]Sashank J. Reddi, Ahmed Hefny, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Stochastic Variance Reduction for Nonconvex Optimization. CoRR abs/1603.06160 (2016) - [i22]Ke Jiang, Suvrit Sra, Brian Kulis:
Combinatorial Topic Models using Small-Variance Asymptotics. CoRR abs/1604.02027 (2016) - [i21]Sashank J. Reddi, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Fast Stochastic Methods for Nonsmooth Nonconvex Optimization. CoRR abs/1605.06900 (2016) - [i20]Hongyi Zhang, Sashank J. Reddi, Suvrit Sra:
Fast stochastic optimization on Riemannian manifolds. CoRR abs/1605.07147 (2016) - [i19]Zelda Mariet, Suvrit Sra:
Kronecker Determinantal Point Processes. CoRR abs/1605.08374 (2016) - [i18]Chengtao Li, Stefanie Jegelka, Suvrit Sra:
Fast Sampling for Strongly Rayleigh Measures with Application to Determinantal Point Processes. CoRR abs/1607.03559 (2016) - [i17]Pourya Zadeh, Reshad Hosseini, Suvrit Sra:
Geometric Mean Metric Learning. CoRR abs/1607.05002 (2016) - [i16]Sashank J. Reddi, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
Stochastic Frank-Wolfe Methods for Nonconvex Optimization. CoRR abs/1607.08254 (2016) - 2015
- [j11]Suvrit Sra, Reshad Hosseini:
Conic Geometric Optimization on the Manifold of Positive Definite Matrices. SIAM J. Optim. 25(1): 713-739 (2015) - [c35]Suvrit Sra, Reshad Hosseini, Lucas Theis, Matthias Bethge:
Data modeling with the elliptical gamma distribution. AISTATS 2015 - [c34]Zelda Mariet, Suvrit Sra:
Fixed-point algorithms for learning determinantal point processes. ICML 2015: 2389-2397 - [c33]Reshad Hosseini, Suvrit Sra:
Matrix Manifold Optimization for Gaussian Mixtures. NIPS 2015: 910-918 - [c32]Sashank J. Reddi, Ahmed Hefny, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants. NIPS 2015: 2647-2655 - [c31]Sashank J. Reddi, Ahmed Hefny, Carlton Downey, Avinava Dubey, Suvrit Sra:
Large-scale randomized-coordinate descent methods with non-separable linear constraints. UAI 2015: 762-771 - [i15]K. S. Sesh Kumar, Álvaro Barbero Jiménez, Stefanie Jegelka, Suvrit Sra, Francis R. Bach:
Convex Optimization for Parallel Energy Minimization. CoRR abs/1503.01563 (2015) - [i14]Sashank J. Reddi, Ahmed Hefny, Suvrit Sra, Barnabás Póczos, Alexander J. Smola:
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants. CoRR abs/1506.06840 (2015) - [i13]Reshad Hosseini, Suvrit Sra:
Manifold Optimization for Gaussian Mixture Models. CoRR abs/1506.07677 (2015) - [i12]Anoop Cherian, Suvrit Sra:
Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices. CoRR abs/1507.02772 (2015) - [i11]Zelda Mariet, Suvrit Sra:
Fixed-point algorithms for determinantal point processes. CoRR abs/1508.00792 (2015) - [i10]Suvrit Sra, Adams Wei Yu, Mu Li, Alexander J. Smola:
AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization. CoRR abs/1508.05003 (2015) - [i9]Chengtao Li, Stefanie Jegelka, Suvrit Sra:
Efficient Sampling for k-Determinantal Point Processes. CoRR abs/1509.01618 (2015) - [i8]Adams Wei Yu, Wanli Ma, Yaoliang Yu, Jaime G. Carbonell, Suvrit Sra:
Efficient Structured Matrix Rank Minimization. CoRR abs/1509.02447 (2015) - [i7]Chengtao Li, Suvrit Sra, Stefanie Jegelka:
Bounds on bilinear inverse forms via Gaussian quadrature with applications. CoRR abs/1512.01904 (2015) - 2014
- [j10]Anoop Cherian, Suvrit Sra, Vassilios Morellas, Nikolaos Papanikolopoulos:
Efficient Nearest Neighbors via Robust Sparse Hashing. IEEE Trans. Image Process. 23(8): 3646-3655 (2014) - [c30]Anoop Cherian, Suvrit Sra:
Riemannian Sparse Coding for Positive Definite Matrices. ECCV (3) 2014: 299-314 - [c29]Samaneh Azadi, Suvrit Sra:
Towards an optimal stochastic alternating direction method of multipliers. ICML 2014: 620-628 - [c28]David Lopez-Paz, Suvrit Sra, Alexander J. Smola, Zoubin Ghahramani, Bernhard Schölkopf:
Randomized Nonlinear Component Analysis. ICML 2014: 1359-1367 - [c27]Adams Wei Yu, Wanli Ma, Yaoliang Yu, Jaime G. Carbonell, Suvrit Sra:
Efficient Structured Matrix Rank Minimization. NIPS 2014: 1350-1358 - [c26]Matt Wytock, Suvrit Sra, Jeremy Z. Kolter:
Fast Newton methods for the group fused lasso. UAI 2014: 888-897 - [p1]Suvrit Sra:
Tractable Optimization in Machine Learning. Tractability 2014: 202-230 - [i6]David Lopez-Paz, Suvrit Sra, Alexander J. Smola, Zoubin Ghahramani, Bernhard Schölkopf:
Randomized Nonlinear Component Analysis. CoRR abs/1402.0119 (2014) - 2013
- [j9]Suvrit Sra, Dmitrii Karp:
The multivariate Watson distribution: Maximum-likelihood estimation and other aspects. J. Multivar. Anal. 114: 256-269 (2013) - [j8]Dongmin Kim, Suvrit Sra, Inderjit S. Dhillon:
A non-monotonic method for large-scale non-negative least squares. Optim. Methods Softw. 28(5): 1012-1039 (2013) - [j7]Anoop Cherian, Suvrit Sra, Arindam Banerjee, Nikolaos Papanikolopoulos:
Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices. IEEE Trans. Pattern Anal. Mach. Intell. 35(9): 2161-2174 (2013) - [c25]Stefanie Jegelka, Francis R. Bach, Suvrit Sra:
Reflection methods for user-friendly submodular optimization. NIPS 2013: 1313-1321 - [c24]Suvrit Sra, Reshad Hosseini:
Geometric optimisation on positive definite matrices for elliptically contoured distributions. NIPS 2013: 2562-2570 - [i5]Stefanie Jegelka, Francis R. Bach, Suvrit Sra:
Reflection methods for user-friendly submodular optimization. CoRR abs/1311.4296 (2013) - [i4]Mikhail A. Langovoy, Suvrit Sra:
Statistical estimation for optimization problems on graphs. CoRR abs/1311.7656 (2013) - 2012
- [j6]Suvrit Sra:
A short note on parameter approximation for von Mises-Fisher distributions: and a fast implementation of I s (x). Comput. Stat. 27(1): 177-190 (2012) - [j5]Suvrit Sra:
Fast projections onto mixed-norm balls with applications. Data Min. Knowl. Discov. 25(2): 358-377 (2012) - [c23]Suvrit Sra:
A new metric on the manifold of kernel matrices with application to matrix geometric means. NIPS 2012: 144-152 - [c22]Suvrit Sra:
Scalable nonconvex inexact proximal splitting. NIPS 2012: 539-547 - [i3]Suvrit Sra:
Fast projections onto mixed-norm balls with applications. CoRR abs/1204.1437 (2012) - 2011
- [c21]Anoop Cherian, Suvrit Sra, Nikolaos Papanikolopoulos:
Denoising sparse noise via online dictionary learning. ICASSP 2011: 2060-2063 - [c20]Anoop Cherian, Suvrit Sra, Arindam Banerjee, Nikolaos Papanikolopoulos:
Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence. ICCV 2011: 2399-2406 - [c19]Álvaro Barbero Jiménez, Suvrit Sra:
Fast Newton-type Methods for Total Variation Regularization. ICML 2011: 313-320 - [c18]Suvrit Sra:
Fast Projections onto ℓ1, q -Norm Balls for Grouped Feature Selection. ECML/PKDD (3) 2011: 305-317 - [c17]Suvrit Sra, Anoop Cherian:
Generalized Dictionary Learning for Symmetric Positive Definite Matrices with Application to Nearest Neighbor Retrieval. ECML/PKDD (3) 2011: 318-332 - 2010
- [j4]Dongmin Kim, Suvrit Sra, Inderjit S. Dhillon:
Tackling Box-Constrained Optimization via a New Projected Quasi-Newton Approach. SIAM J. Sci. Comput. 32(6): 3548-3563 (2010) - [c16]Michael Hirsch, Suvrit Sra, Bernhard Schölkopf, Stefan Harmeling:
Efficient filter flow for space-variant multiframe blind deconvolution. CVPR 2010: 607-614 - [c15]Stefan Harmeling, Suvrit Sra, Michael Hirsch, Bernhard Schölkopf:
Multiframe blind deconvolution, super-resolution, and saturation correction via incremental EM. ICIP 2010: 3313-3316 - [c14]Dongmin Kim, Suvrit Sra, Inderjit S. Dhillon:
A scalable trust-region algorithm with application to mixed-norm regression. ICML 2010: 519-526
2000 – 2009
- 2009
- [c13]Stefanie Jegelka, Suvrit Sra, Arindam Banerjee:
Approximation Algorithms for Tensor Clustering. ALT 2009: 368-383 - [c12]Matthias W. Seeger, Suvrit Sra, John P. Cunningham:
Workshop summary: Numerical mathematics in machine learning. ICML 2009: 9 - [c11]Brian Kulis, Suvrit Sra, Inderjit S. Dhillon:
Convex Perturbations for Scalable Semidefinite Programming. AISTATS 2009: 296-303 - [i2]Suvrit Sra:
A Trivial Observation related to Sparse Recovery. CoRR abs/0906.4805 (2009) - 2008
- [j3]Dongmin Kim, Suvrit Sra, Inderjit S. Dhillon:
Fast Projection-Based Methods for the Least Squares Nonnegative Matrix Approximation Problem. Stat. Anal. Data Min. 1(1): 38-51 (2008) - [j2]Justin Brickell, Inderjit S. Dhillon, Suvrit Sra, Joel A. Tropp:
The Metric Nearness Problem. SIAM J. Matrix Anal. Appl. 30(1): 375-396 (2008) - [c10]Suvrit Sra:
Block-Iterative Algorithms for Non-negative Matrix Approximation. ICDM 2008: 1037-1042 - [i1]Stefanie Jegelka, Suvrit Sra, Arindam Banerjee:
Approximation Algorithms for Bregman Co-clustering and Tensor Clustering. CoRR abs/0812.0389 (2008) - 2007
- [c9]Jason V. Davis, Brian Kulis, Prateek Jain, Suvrit Sra, Inderjit S. Dhillon:
Information-theoretic metric learning. ICML 2007: 209-216 - [c8]Dongmin Kim, Suvrit Sra, Inderjit S. Dhillon:
Fast Newton-type Methods for the Least Squares Nonnegative Matrix Approximation Problem. SDM 2007: 343-354 - 2006
- [c7]Suvrit Sra:
Efficient Large Scale Linear Programming Support Vector Machines. ECML 2006: 767-774 - [c6]Suvrit Sra, Joel A. Tropp:
Row-Action Methods for Compressed Sensing. ICASSP (3) 2006: 868-871 - [c5]Arun C. Surendran, Suvrit Sra:
Incremental Aspect Models for Mining Document Streams. PKDD 2006: 633-640 - 2005
- [j1]Arindam Banerjee, Inderjit S. Dhillon, Joydeep Ghosh, Suvrit Sra:
Clustering on the Unit Hypersphere using von Mises-Fisher Distributions. J. Mach. Learn. Res. 6: 1345-1382 (2005) - [c4]Inderjit S. Dhillon, Suvrit Sra:
Generalized Nonnegative Matrix Approximations with Bregman Divergences. NIPS 2005: 283-290 - 2004
- [c3]Inderjit S. Dhillon, Suvrit Sra, Joel A. Tropp:
Triangle Fixing Algorithms for the Metric Nearness Problem. NIPS 2004: 361-368 - [c2]Hyuk Cho, Inderjit S. Dhillon, Yuqiang Guan, Suvrit Sra:
Minimum Sum-Squared Residue Co-Clustering of Gene Expression Data. SDM 2004: 114-125 - 2003
- [c1]Arindam Banerjee, Inderjit S. Dhillon, Joydeep Ghosh, Suvrit Sra:
Generative model-based clustering of directional data. KDD 2003: 19-28
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-28 21:23 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
