Suvrit Sra
#150,846
Most Influential Person Now
Researcher
Suvrit Sra's AcademicInfluence.com Rankings
Suvrit Sraengineering Degrees
Engineering
#6090
World Rank
#7394
Historical Rank
Electrical Engineering
#1766
World Rank
#1865
Historical Rank

Suvrit Sracomputer-science Degrees
Computer Science
#7927
World Rank
#8343
Historical Rank
Theoretical Computer Science
#100
World Rank
#100
Historical Rank
Data Science
#170
World Rank
#173
Historical Rank
Algorithms
#312
World Rank
#316
Historical Rank

Download Badge
Engineering Computer Science
Suvrit Sra's Degrees
- Bachelors Computer Science and Engineering IIT Bombay
Why Is Suvrit Sra Influential?
(Suggest an Edit or Addition)Suvrit Sra's Published Works
Number of citations in a given year to any of this author's works
Total number of citations to an author for the works they published in a given year. This highlights publication of the most important work(s) by the author
Published Works
- Information-theoretic metric learning (2006) (1931)
- Clustering on the Unit Hypersphere using von Mises-Fisher Distributions (2005) (888)
- Stochastic Variance Reduction for Nonconvex Optimization (2016) (510)
- Generalized Nonnegative Matrix Approximations with Bregman Divergences (2005) (484)
- Minimum Sum-Squared Residue Co-Clustering of Gene Expression Data (2004) (328)
- Contrastive Learning with Hard Negative Samples (2020) (306)
- Efficient filter flow for space-variant multiframe blind deconvolution (2010) (236)
- First-order Methods for Geodesically Convex Optimization (2016) (214)
- Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity (2019) (207)
- On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants (2015) (191)
- Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds (2016) (175)
- Randomized Nonlinear Component Analysis (2014) (168)
- Optimization for Machine Learning (2013) (165)
- Entropic metric alignment for correspondence problems (2016) (164)
- Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices (2013) (159)
- Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization (2016) (158)
- Geometric Mean Metric Learning (2016) (140)
- Fast Newton-type Methods for the Least Squares Nonnegative Matrix Approximation Problem (2007) (139)
- A short note on parameter approximation for von Mises-Fisher distributions: and a fast implementation of Is(x) (2012) (137)
- Conic Geometric Optimization on the Manifold of Positive Definite Matrices (2013) (136)
- A new metric on the manifold of kernel matrices with application to matrix geometric means (2012) (134)
- Generative model-based clustering of directional data (2003) (122)
- Stochastic Frank-Wolfe methods for nonconvex optimization (2016) (120)
- Global optimality conditions for deep neural networks (2017) (119)
- Matrix Differential Calculus (2005) (117)
- Positive definite matrices and the S-divergence (2011) (110)
- Why are Adaptive Methods Good for Attention Models? (2020) (108)
- Modular Proximal Optimization for Multidimensional Total-Variation Regularization (2014) (105)
- Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices (2015) (105)
- Modeling Data using Directional Distributions (2003) (100)
- Direct Runge-Kutta Discretization Achieves Acceleration (2018) (96)
- Tackling Box-Constrained Optimization via a New Projected Quasi-Newton Approach (2010) (91)
- Fast Newton-type Methods for Total Variation Regularization (2011) (87)
- Small nonlinearities in activation functions create bad local minima in neural networks (2018) (84)
- A Generic Approach for Escaping Saddle points (2017) (81)
- Projected Newton-type methods in machine learning (2011) (79)
- Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity (2018) (79)
- Matrix Manifold Optimization for Gaussian Mixtures (2015) (78)
- Reflection methods for user-friendly submodular optimization (2013) (77)
- Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence (2011) (77)
- Fast DPP Sampling for Nystrom with Application to Kernel Methods (2016) (76)
- Nonnegative Matrix Approximation: Algorithms and Applications (2006) (75)
- The multivariate Watson distribution: Maximum-likelihood estimation and other aspects (2011) (73)
- Random Shuffling Beats SGD after Finite Epochs (2018) (69)
- Positive definite matrices and the Symmetric Stein Divergence (2011) (65)
- Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition (2020) (64)
- Scalable nonconvex inexact proximal splitting (2012) (64)
- Fast incremental method for smooth nonconvex optimization (2016) (64)
- A non-monotonic method for large-scale non-negative least squares (2013) (63)
- Why ADAM Beats SGD for Attention Models (2019) (62)
- Escaping Saddle Points with Adaptive Gradient Methods (2019) (61)
- Diversity Networks: Neural Network Compression Using Determinantal Point Processes (2015) (60)
- Towards an optimal stochastic alternating direction method of multipliers (2014) (60)
- Diversity Networks (2015) (56)
- Riemannian Sparse Coding for Positive Definite Matrices (2014) (55)
- Can contrastive learning avoid shortcut solutions? (2021) (55)
- From Nesterov's Estimate Sequence to Riemannian Acceleration (2020) (55)
- Multiframe blind deconvolution, super-resolution, and saturation correction via incremental EM (2010) (53)
- The Metric Nearness Problem (2008) (53)
- Fast Stochastic Methods for Nonsmooth Nonconvex Optimization (2016) (51)
- Efficient Sampling for k-Determinantal Point Processes (2015) (51)
- Generalized Dictionary Learning for Symmetric Positive Definite Matrices with Application to Nearest Neighbor Retrieval (2011) (50)
- Online blind deconvolution for astronomical imaging (2009) (50)
- Online Multi-frame Blind Deconvolution with Super-resolution and Saturation Correction (2011) (48)
- An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization (2017) (47)
- Approximation Algorithms for Tensor Clustering (2009) (46)
- An Estimate Sequence for Geodesically Convex Optimization (2018) (45)
- Fixed-point algorithms for learning determinantal point processes (2015) (44)
- Fast Incremental Method for Nonconvex Optimization (2016) (43)
- Minimum Sum-Squared Residue based clustering of Gene Expression Data (2004) (42)
- Sign and Basis Invariant Networks for Spectral Graph Representation Learning (2022) (41)
- A scalable trust-region algorithm with application to mixed-norm regression (2010) (41)
- Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator (2019) (40)
- Non-linear Temporal Subspace Representations for Activity Recognition (2018) (39)
- Towards Riemannian Accelerated Gradient Methods (2018) (39)
- Fast Projection‐Based Methods for the Least Squares Nonnegative Matrix Approximation Problem (2008) (39)
- Fast Projections onto ℓ1, q -Norm Balls for Grouped Feature Selection (2011) (39)
- Directional Statistics in Machine Learning: A Brief Review Suvrit Sra (2016) (38)
- Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms (2014) (38)
- A New Projected Quasi-Newton Approach for the Nonnegative Least Squares Problem (2006) (36)
- Fast stochastic optimization on Riemannian manifolds (2016) (36)
- On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions (2020) (35)
- Sparse nonnegative matrix approximation: new formulations and algorithms (2010) (34)
- Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling (2016) (34)
- R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate (2018) (33)
- Coping with Label Shift via Distributionally Robust Optimisation (2020) (33)
- Online Learning in Unknown Markov Games (2021) (32)
- SGD with shuffling: optimal rates without component convexity and large epoch requirements (2020) (32)
- Polynomial time algorithms for dual volume sampling (2017) (32)
- A Critical View of Global Optimality in Deep Learning (2018) (31)
- AdaDelay: Delay Adaptive Distributed Stochastic Optimization (2016) (31)
- Geometric optimisation on positive definite matrices for elliptically contoured distributions (2013) (29)
- Fast projections onto mixed-norm balls with applications (2012) (29)
- AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization (2015) (29)
- Kronecker Determinantal Point Processes (2016) (26)
- Strength from Weakness: Fast Learning Using Weak Supervision (2020) (25)
- Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes (2020) (22)
- Deep-RBF Networks Revisited: Robust Classification with Rejection (2018) (22)
- Large-scale randomized-coordinate descent methods with non-separable linear constraints (2014) (21)
- Fast Projection-Based Methods for the Least Squares Nonnegative Matrix Approximation Problem (2008) (21)
- Non-monotonic Poisson Likelihood Maximization (2008) (21)
- Efficient Nearest Neighbors via Robust Sparse Hashing (2014) (21)
- Efficient Structured Matrix Rank Minimization (2014) (20)
- Triangle Fixing Algorithms for the Metric Nearness Problem (2004) (20)
- Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond (2021) (20)
- Elementary Symmetric Polynomials for Optimal Experimental Design (2017) (20)
- Understanding the unstable convergence of gradient descent (2022) (19)
- Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions (2020) (19)
- Efficient Large Scale Linear Programming Support Vector Machines (2006) (19)
- Incremental Aspect Models for Mining Document Streams (2006) (18)
- Fast Newton methods for the group fused lasso (2014) (18)
- Row-Action Methods for Compressed Sensing (2006) (18)
- On the matrix square root via geometric optimization (2015) (18)
- Geometric Optimization in Machine Learning (2016) (18)
- The sum of squared logarithms inequality in arbitrary dimensions (2015) (17)
- Gaussian quadrature for matrix inverse forms with applications (2015) (15)
- Distributional Adversarial Networks (2017) (15)
- Denoising sparse noise via online dictionary learning (2011) (15)
- Provably Efficient Algorithms for Multi-Objective Competitive RL (2021) (14)
- Projection-free nonconvex stochastic optimization on Riemannian manifolds (2019) (14)
- Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods (2019) (13)
- Exponentiated Strongly Rayleigh Distributions (2018) (12)
- Positive Definite Matrices: Data Representation and Applications to Computer Vision (2016) (12)
- Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? (2021) (12)
- Approximation Algorithms for Bregman Clustering Co-clustering and Tensor Clustering (2008) (11)
- Flexible Modeling of Diversity with Strongly Log-Concave Distributions (2019) (11)
- Metrics induced by Jensen-Shannon and related divergences on positive definite matrices (2019) (11)
- Why do classifier accuracies show linear trends under distribution shift? (2020) (11)
- Matrix nearness problems in data mining (2007) (11)
- Hlawka-Popoviciu inequalities on positive definite tensors (2014) (11)
- On inequalities for normalized Schur functions (2015) (11)
- Are deep ResNets provably better than linear predictors? (2019) (11)
- Fast algorithms for total-variation based optimization (2010) (10)
- Introduction: Optimization and Machine Learning (2011) (10)
- Nonconvex proximal splitting: batch and incremental algorithms (2011) (9)
- Convex Perturbations for Scalable Semidefinite Programming (2009) (9)
- Generalized Proximity and Projection with Norms and Mixed-norms (2010) (9)
- Frank-Wolfe methods for geodesically convex optimization with application to the matrix geometric mean (2017) (9)
- Analysis of Gradient Clipping and Adaptive Scaling with a Relaxed Smoothness Condition (2019) (9)
- Provably Efficient Online Agnostic Learning in Markov Games (2020) (9)
- Recent Advances in Stochastic Riemannian Optimization (2020) (8)
- Convex Optimization for Parallel Energy Minimization (2015) (8)
- Efficiently testing local optimality and escaping saddles for ReLU networks (2018) (8)
- Max-Margin Contrastive Learning (2021) (8)
- Fixed-point algorithms for determinantal point processes (2015) (8)
- Minimax in Geodesic Metric Spaces: Sion's Theorem and Algorithms (2022) (7)
- Portfolio Optimization with Groupwise Selection (2014) (7)
- Asynchronous Parallel Block-Coordinate Frank-Wolfe (2014) (7)
- Riemannian Optimization via Frank-Wolfe Methods (2017) (7)
- Correlation matrix nearness and completion under observation uncertainty (2015) (7)
- A proof of Thompson’S determinantal inequality (2016) (6)
- Data modeling with the elliptical gamma distribution (2015) (6)
- Completely strong superadditivity of generalized matrix functions (2014) (6)
- Fast Sampling for Strongly Rayleigh Measures with Application to Determinantal Point Processes (2016) (6)
- Block-Iterative Algorithms for Non-negative Matrix Approximation (2008) (6)
- Learning Determinantal Point Processes by Corrective Negative Sampling (2018) (6)
- Modeling data using directional distributions: Part II (2007) (6)
- Acceleration in First Order Quasi-strongly Convex Optimization by ODE Discretization (2019) (5)
- Approximation Algorithms for Bregman Co-clustering and Tensor Clustering (2008) (5)
- Geometric optimisation on positive definite matrices with application to elliptically contoured distributions (2013) (5)
- Inference and mixture modeling with the Elliptical Gamma Distribution (2014) (5)
- Scalable Semidefinite Programming using Convex Perturbations (2007) (5)
- Finite sample expressive power of small-width ReLU networks (2018) (5)
- Expectation Maximization for Clustering on Hyperspheres (2003) (5)
- New concavity and convexity results for symmetric polynomials and their ratios (2018) (5)
- On Tight Convergence Rates of Without-replacement SGD (2020) (4)
- A THEORETICAL JUSTIFICATION FOR ADAPTIVITY (2020) (4)
- An Interpretable Predictive Model of Vaccine Utilization for Tanzania (2020) (4)
- Manifold Optimization for Gaussian Mixture Models (2015) (4)
- Jensen-Bregman LogDet Divergence for Efficient Similarity Computations on Positive Definite Tensors (2012) (4)
- Logarithmic inequalities under a symmetric polynomial dominance order (2017) (4)
- Three Operator Splitting with a Nonconvex Loss Function (2021) (4)
- Theory and Algorithms for Diffusion Processes on Riemannian Manifolds (2022) (3)
- CCCP is Frank-Wolfe in disguise (2022) (3)
- Column Subset Selection via Polynomial Time Dual Volume Sampling (2017) (3)
- A Riemannian Accelerated Proximal Extragradient Framework and its Implications (2021) (3)
- Learning Determinantal Point Processes by Sampling Inferred Negatives (2018) (3)
- Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective (2021) (3)
- A New Non-monotonic Gradient Projection Method for the Non-negative Least Squares Problem (2008) (3)
- Understanding Riemannian Acceleration via a Proximal Extragradient Framework (2021) (2)
- Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation (2019) (2)
- A new non-monotonic algorithm for PET image reconstruction (2009) (2)
- Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates (2021) (2)
- The Metric Nearness Problem with Applications (2003) (2)
- Stochastic Optimization with Non-stationary Noise (2020) (2)
- Combinatorial Topic Models using Small-Variance Asymptotics (2016) (2)
- Statistical inference with the Elliptical Gamma Distribution (2014) (2)
- Geodesically-convex optimization for averaging partially observed covariance matrices (2020) (2)
- Optimal Batch Variance with Second-Order Marginals (2020) (2)
- Unsupervised robust nonparametric learning of hidden community properties (2017) (2)
- Text Clustering with Mixture of von Mises-Fisher Distributions (2009) (2)
- Markov Chain Sampling in Discrete Probabilistic Models with Constraints (2016) (2)
- Understanding Nesterov's Acceleration via Proximal Point Method (2020) (2)
- Positive Definite Matrices: Symmetric positive definite (SPD) matrices Data RepresentationData representation and Applications to Computer Vision (2016) (2)
- Near Optimal Stratified Sampling (2019) (2)
- On Convergence of Training Loss Without Reaching Stationary Points (2021) (2)
- On a class of geodesically convex optimization problems solved via Euclidean MM methods (2022) (2)
- Riemannian Frank-Wolfe with application to the geometric mean of positive definite matrices (2017) (1)
- Logarithmic inequalities under an elementary symmetric polynomial dominance order (2015) (1)
- Metrics Induced by Quantum Jensen-Shannon-Renyí and Related Divergences (2019) (1)
- A short note on parameter approximation for von Mises-Fisher distributions: and a fast implementation of Is(x) (2011) (1)
- Bounds on bilinear inverse forms via Gaussian quadrature with applications (2015) (1)
- Solving large-scale nonnegative least squares using an adaptive non-monotonic method (2010) (1)
- Computing Brascamp-Lieb Constants through the lens of Thompson Geometry (2022) (1)
- An Incremental GEM Framework for Multiframe Blind Deconvolution, Super-Resolution, and Saturation Correction (2009) (1)
- Inequalities via symmetric polynomial majorization (2015) (1)
- Positive definite functions of noncommuting contractions, Hua-Bellman matrices, and a new distance metric (2021) (1)
- Sparse Inverse Covariance Estimation via an Adaptive Gradient-Based Method (2011) (1)
- Time Varying Regression with Hidden Linear Dynamics (2021) (1)
- Explicit diagonalization of an anti-triangular Cesar\'o matrix (2014) (1)
- Tractable Optimization in Machine Learning (2014) (1)
- Sequence Summarization Using Order-constrained Kernelized Feature Subspaces (2017) (1)
- Modeling data using directional distributions : Part II Suvrit Sra (2007) (0)
- Efficient Sampling on Riemannian Manifolds via Langevin MCMC (2022) (0)
- Spurious local minima in neural networks: a critical view (2018) (0)
- Sparse regression via a trust-region proximal method (2010) (0)
- HARD NEGATIVE SAMPLES (2021) (0)
- Recent (2021) (0)
- Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity (2020) (0)
- New Projected Quasi-Newton Methods with Applications (2008) (0)
- Fast projections onto mixed-norm balls with applications (2012) (0)
- Non-monotonic Poisson (2008) (0)
- Explicit eigenvalues of certain scaled trigonometric matrices (2012) (0)
- An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization (2019) (0)
- LOBAL OPTIMALITY CONDITIONS FOR DEEP NEURAL NETWORKS (2018) (0)
- Introducing Discrepancy Values of Matrices with Application to Bounding Norms of Commutators (2021) (0)
- Nonconvex proximal splitting with computational errors ∗ (2016) (0)
- Statement of Research (2002) (0)
- On the Training Instability of Shuffling SGD with Batch Normalization (2023) (0)
- Sparse Recovery without the Restricted Isometry Property (2009) (0)
- Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control? (2022) (0)
- The Hornich-Hlawka functional inequality for functions with positive differences (2023) (0)
- Statistical estimation for optimization problems on graphs (2011) (0)
- Matrix Approximation Problems (2010) (0)
- Solving large-scale nonnegative least-squares (2010) (0)
- Supplementary Material for Combinatorial Topic Models using Small-Variance Asymptotics (2017) (0)
- A proof of Thompson’S determinantal inequality (2016) (0)
- Workshop summary: Numerical mathematics in machine learning (2009) (0)
- A Trivial Observation related to Sparse Recovery (2009) (0)
- Generalized Hlawka inequalities on positive definite tensors (2014) (0)
This paper list is powered by the following services:
What Schools Are Affiliated With Suvrit Sra?
Suvrit Sra is affiliated with the following schools: