Suvrit Sra

发表

Sequence Summarization Using Order-constrained Kernelized Feature Subspaces pdf

Anoop Cherian, Richard Hartley, Suvrit Sra, 2017, ArXiv.

Manifold Optimization for Gaussian Mixture Models pdf

Suvrit Sra, Reshad Hosseini, 2015, ArXiv.

Why do classifier accuracies show linear trends under distribution shift? pdf

Suvrit Sra, Horia Mania, 2020, ArXiv.

Learning Determinantal Point Processes by Corrective Negative Sampling

Suvrit Sra, Zelda Mariet, Mike Gartrell, 2019, AISTATS.

Generative model-based clustering of directional data

Inderjit S. Dhillon, Suvrit Sra, Joydeep Ghosh, 2003, KDD '03.

Data modeling with the elliptical gamma distribution

Matthias Bethge, Suvrit Sra, Reshad Hosseini, 2015, AISTATS.

Workshop summary: Numerical mathematics in machine learning

Suvrit Sra, John P. Cunningham, Matthias W. Seeger, 2009, ICML '09.

Distributional Adversarial Networks pdf

Suvrit Sra, Stefanie Jegelka, Keyulu Xu, 2018, ICLR.

Multiframe blind deconvolution, super-resolution, and saturation correction via incremental EM

Bernhard Schölkopf, Suvrit Sra, Michael Hirsch, 2010, 2010 IEEE International Conference on Image Processing.

Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds

Suvrit Sra, Sashank J. Reddi, Hongyi Zhang, 2016, NIPS.

Fast Projections onto ℓ1, q -Norm Balls for Grouped Feature Selection

Suvrit Sra, S. Sra, 2011, ECML/PKDD.

Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition

Haipeng Luo, Suvrit Sra, Chi Jin, 2020, ICML.

The multivariate Watson distribution: Maximum-likelihood estimation and other aspects

Suvrit Sra, Dmitrii Karp, 2013, J. Multivar. Anal..

Fixed-point algorithms for learning determinantal point processes

Suvrit Sra, Zelda Mariet, 2015, ICML.

A scalable trust-region algorithm with application to mixed-norm regression

Inderjit S. Dhillon, Suvrit Sra, Dongmin Kim, 2010, ICML.

Fast DPP Sampling for Nystrom with Application to Kernel Methods pdf

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2016, ICML.

Efficient filter flow for space-variant multiframe blind deconvolution

Bernhard Schölkopf, Suvrit Sra, Michael Hirsch, 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

Fast stochastic optimization on Riemannian manifolds pdf

Suvrit Sra, Sashank J. Reddi, Hongyi Zhang, 2016, ArXiv.

Anoop Cherian, Nikolaos Papanikolopoulos, Suvrit Sra, 2011, 2011 International Conference on Computer Vision.

Towards Riemannian Accelerated Gradient Methods pdf

Suvrit Sra, Hongyi Zhang, S. Sra, 2018, ArXiv.

Fast Sampling for Strongly Rayleigh Measures with Application to Determinantal Point Processes pdf

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2016, ArXiv.

Stochastic Variance Reduction for Nonconvex Optimization

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2016, ICML.

Recent Advances in Stochastic Riemannian Optimization

Suvrit Sra, Reshad Hosseini, S. Sra, 2020 .

Minimum Sum-Squared Residue based clustering of Gene Expression Data

Suvrit Sra, H Cho, Dhillon I Guan Y, 2004 .

Convex Perturbations for Scalable Semidefinite Programming

Inderjit S. Dhillon, Suvrit Sra, Brian Kulis, 2009, AISTATS.

A Trivial Observation related to Sparse Recovery pdf

Suvrit Sra, 2009, ArXiv.

Escaping Saddle Points with Adaptive Gradient Methods

Sanjiv Kumar, Suvrit Sra, Sashank J. Reddi, 2019, ICML.

Reflection methods for user-friendly submodular optimization

Suvrit Sra, Francis Bach, Stefanie Jegelka, 2013, NIPS.

Geodesically-convex optimization for averaging partially observed covariance matrices

Florian Yger, Sylvain Chevallier, Suvrit Sra, 2020, ACML.

Bounds on bilinear inverse forms via Gaussian quadrature with applications pdf

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2015, ArXiv.

A Generic Approach for Escaping Saddle points

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2017, AISTATS.

Analysis of Gradient Clipping and Adaptive Scaling with a Relaxed Smoothness Condition pdf

Suvrit Sra, Ali Jadbabaie, Jingzhao Zhang, 2019, ArXiv.

Stochastic Optimization with Non-stationary Noise pdf

Suvrit Sra, Subhro Das, Ali Jadbabaie, 2020, ArXiv.

Minimum Sum-Squared Residue Co-Clustering of Gene Expression Data

Inderjit S. Dhillon, Suvrit Sra, Hyuk Cho, 2004, SDM.

A Critical View of Global Optimality in Deep Learning pdf

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2018, ArXiv.

Metrics Induced by Jensen-Shannon and Related Divergences on Positive Definite Matrices

Suvrit Sra, 2019 .

Convex Optimization for Parallel Energy Minimization pdf

Suvrit Sra, Francis R. Bach, Stefanie Jegelka, 2015, ArXiv.

Exponentiated Strongly Rayleigh Distributions

Suvrit Sra, Stefanie Jegelka, Zelda E. Mariet, 2018, NeurIPS.

Conic Geometric Optimization on the Manifold of Positive Definite Matrices

Suvrit Sra, Reshad Hosseini, 2015, SIAM J. Optim..

Deep-RBF Networks Revisited: Robust Classification with Rejection pdf

Suvrit Sra, Reshad Hosseini, Pourya Habib Zadeh, 2018, ArXiv.

Modular Proximal Optimization for Multidimensional Total-Variation Regularization

Suvrit Sra, Álvaro Barbero Jiménez, S. Sra, 2014, J. Mach. Learn. Res..

Flexible Modeling of Diversity with Strongly Log-Concave Distributions

Suvrit Sra, Stefanie Jegelka, Joshua Robinson, 2019, NeurIPS.

Random Shuffling Beats SGD after Finite Epochs

Suvrit Sra, Jeff Haochen, Jeff Z. HaoChen, 2018, ICML.

Global optimality conditions for deep neural networks pdf

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2017, ICLR.

Are deep ResNets provably better than linear predictors?

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2019, NeurIPS.

Clustering on the Unit Hypersphere using von Mises-Fisher Distributions

Inderjit S. Dhillon, Suvrit Sra, Joydeep Ghosh, 2005, J. Mach. Learn. Res..

Fast Stochastic Methods for Nonsmooth Nonconvex Optimization pdf

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2016, ArXiv.

First-order Methods for Geodesically Convex Optimization

Suvrit Sra, Hongyi Zhang, S. Sra, 2016, COLT.

A non-monotonic method for large-scale non-negative least squares

Inderjit S. Dhillon, Suvrit Sra, Dongmin Kim, 2013, Optim. Methods Softw..

Fast Newton-type Methods for the Least Squares Nonnegative Matrix Approximation Problem

Inderjit S. Dhillon, Suvrit Sra, Dongmin Kim, 2007, SDM.

Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator

Volkan Cevher, Suvrit Sra, Alp Yurtsever, 2019, ICML.

Statistical estimation for optimization problems on graphs pdf

Suvrit Sra, Mikhail A. Langovoy, 2011, NIPS 2011.

Approximation Algorithms for Bregman Co-clustering and Tensor Clustering pdf

Suvrit Sra, Arindam Banerjee, Stefanie Jegelka, 2008, ArXiv.

Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2016, NIPS.

Learning Determinantal Point Processes by Sampling Inferred Negatives pdf

Suvrit Sra, Mike Gartrell, Zelda Mariet, 2018, ArXiv.

Diversity Networks pdf

Suvrit Sra, Zelda Mariet, S. Sra, 2015, ICLR.

Stochastic Frank-Wolfe methods for nonconvex optimization

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions pdf

Suvrit Sra, Ali Jadbabaie, Jingzhao Zhang, 2020, ArXiv.

Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices

Anoop Cherian, Nikolaos Papanikolopoulos, Suvrit Sra, 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Row-Action Methods for Compressed Sensing

Suvrit Sra, Joel A. Tropp, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2018, NeurIPS.

A short note on parameter approximation for von Mises-Fisher distributions: and a fast implementation of Is(x)

Suvrit Sra, S. Sra, 2012, Comput. Stat..

Tractable Optimization in Machine Learning

Suvrit Sra, S. Sra, 2014, Tractability.

Unsupervised robust nonparametric learning of hidden community properties pdf

Martin Jaggi, Suvrit Sra, Akhilesh Gotmare, 2017, Math. Found. Comput..

Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions

Suvrit Sra, Stefanie Jegelka, Ali Jadbabaie, 2020, ICML.

Efficient Sampling for k-Determinantal Point Processes pdf

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2016, AISTATS.

Elementary Symmetric Polynomials for Optimal Experimental Design

Suvrit Sra, Zelda E. Mariet, S. Sra, 2017, NIPS.

On Tight Convergence Rates of Without-replacement SGD pdf

Suvrit Sra, Kwangjun Ahn, 2020, ArXiv.

Riemannian Sparse Coding for Positive Definite Matrices

Anoop Cherian, Suvrit Sra, S. Sra, 2014, ECCV.

Geometric Mean Metric Learning pdf

Suvrit Sra, Reshad Hosseini, Pourya Zadeh, 2016, ICML.

R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate pdf

Hongyi Zhang, Suvrit Sra, Jingzhao Zhang, 2018, ArXiv.

AdaDelay: Delay Adaptive Distributed Stochastic Optimization

Alexander J. Smola, Suvrit Sra, Mu Li, 2016, AISTATS.

Towards an optimal stochastic alternating direction method of multipliers

Suvrit Sra, Samaneh Azadi, S. Sra, 2014, ICML.

Generalized Nonnegative Matrix Approximations with Bregman Divergences

Inderjit S. Dhillon, Suvrit Sra, I. Dhillon, 2005, NIPS.

Information-theoretic metric learning

Inderjit S. Dhillon, Prateek Jain, Suvrit Sra, 2006, ICML '07.

SGD with shuffling: optimal rates without component convexity and large epoch requirements

Suvrit Sra, Kwangjun Ahn, Chulhee Yun, 2020, NeurIPS.

Geometric Optimization in Machine Learning

Suvrit Sra, Reshad Hosseini, 2016 .

Randomized Nonlinear Component Analysis pdf

Bernhard Schölkopf, Alexander J. Smola, Zoubin Ghahramani, 2014, ICML.

Efficient Structured Matrix Rank Minimization

Yaoliang Yu, Wanli Ma, Jaime G. Carbonell, 2014, NIPS.

Fast Projection-Based Methods for the Least Squares Nonnegative Matrix Approximation Problem

Inderjit S. Dhillon, Suvrit Sra, Dongmin Kim, 2008, Stat. Anal. Data Min..

Efficient Large Scale Linear Programming Support Vector Machines

Suvrit Sra, 2006, ECML.

Polynomial time algorithms for dual volume sampling

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2017, NIPS.

Efficiently testing local optimality and escaping saddles for ReLU networks pdf

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2018, ICLR.

Fast Newton-type Methods for Total Variation Regularization

Suvrit Sra, Álvaro Barbero Jiménez, S. Sra, 2011, ICML.

Large-scale randomized-coordinate descent methods with non-separable linear constraints

Suvrit Sra, Sashank J. Reddi, Avinava Dubey, 2014, UAI.

Direct Runge-Kutta Discretization Achieves Acceleration

Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie, 2018, NeurIPS.

Directional Statistics in Machine Learning: A Brief Review Suvrit Sra

Suvrit Sra, S. Sra, 2016, Applied Directional Statistics.

Geometric optimisation on positive definite matrices for elliptically contoured distributions

Suvrit Sra, Reshad Hosseini, S. Sra, 2013, NIPS.

Incremental Aspect Models for Mining Document Streams

Suvrit Sra, Arun C. Surendran, 2006, PKDD.

Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods pdf

Suvrit Sra, Melanie Weber, 2019, ArXiv.

Matrix Manifold Optimization for Gaussian Mixtures

Suvrit Sra, Reshad Hosseini, S. Sra, 2015, NIPS.

Combinatorial Topic Models using Small-Variance Asymptotics pdf

Ke Jiang, Suvrit Sra, Brian Kulis, 2017, AISTATS.

Diversity Networks: Neural Network Compression Using Determinantal Point Processes

Suvrit Sra, Zelda Mariet, S. Sra, 2015, 1511.05077.

AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization pdf

Alexander J. Smola, Suvrit Sra, Mu Li, 2015, ArXiv.

Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity

Suvrit Sra, Ali Jadbabaie, Jingzhao Zhang, 2019, ICLR.

Fast Incremental Method for Nonconvex Optimization pdf

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2016, ArXiv.

A new metric on the manifold of kernel matrices with application to matrix geometric means

Suvrit Sra, 2012, NIPS.

Strength from Weakness: Fast Learning Using Weak Supervision

Suvrit Sra, Stefanie Jegelka, Joshua Robinson, 2020, ICML.

Frank-Wolfe methods for geodesically convex optimization with application to the matrix geometric mean

Suvrit Sra, Melanie Weber, S. Sra, 2017, ArXiv.

Efficient Nearest Neighbors via Robust Sparse Hashing

Vassilios Morellas, Anoop Cherian, Nikolaos Papanikolopoulos, 2014, IEEE Transactions on Image Processing.

Scalable nonconvex inexact proximal splitting

Suvrit Sra, S. Sra, 2012, NIPS.

Non-linear Temporal Subspace Representations for Activity Recognition

Anoop Cherian, Richard Hartley, Suvrit Sra, 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms

Eric P. Xing, Suvrit Sra, Yu-Xiang Wang, 2014, ICML.

From Nesterov's Estimate Sequence to Riemannian Acceleration

Suvrit Sra, Kwangjun Ahn, S. Sra, 2020, COLT.

On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2015, NIPS.

Small nonlinearities in activation functions create bad local minima in neural networks

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2019, ICLR.

Block-Iterative Algorithms for Non-negative Matrix Approximation

Suvrit Sra, 2008, 2008 Eighth IEEE International Conference on Data Mining.

Acceleration in First Order Quasi-strongly Convex Optimization by ODE Discretization

Suvrit Sra, Ali Jadbabaie, Jingzhao Zhang, 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).

Fast Newton methods for the group fused lasso

Suvrit Sra, J. Zico Kolter, Matt Wytock, 2014, UAI.

Non-monotonic Poisson

Suvrit Sra, Max Planck, Dongmin Kim, 2008 .

An Estimate Sequence for Geodesically Convex Optimization

Suvrit Sra, Hongyi Zhang, S. Sra, 2018, COLT.

An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization

Suvrit Sra, Reshad Hosseini, S. Sra, 2017, Math. Program..

Triangle Fixing Algorithms for the Metric Nearness Problem

Inderjit S. Dhillon, Suvrit Sra, Joel A. Tropp, 2004, NIPS.

Spurious local minima in neural networks: a critical view

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2018 .

Denoising sparse noise via online dictionary learning

Anoop Cherian, Nikolaos Papanikolopoulos, Suvrit Sra, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Entropic metric alignment for correspondence problems

Vladimir G. Kim, Gabriel Peyré, Suvrit Sra, 2016, ACM Trans. Graph..

The Metric Nearness Problem

Inderjit S. Dhillon, Suvrit Sra, Joel A. Tropp, 2008, SIAM J. Matrix Anal. Appl..

Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices

Anoop Cherian, Suvrit Sra, S. Sra, 2015, IEEE Transactions on Neural Networks and Learning Systems.

Approximation Algorithms for Tensor Clustering

Suvrit Sra, Arindam Banerjee, Stefanie Jegelka, 2009, ALT.

Near Optimal Stratified Sampling pdf

Suvrit Sra, Tiancheng Yu, Xiyu Zhai, 2019, ArXiv.

Positive Definite Matrices: Data Representation and Applications to Computer Vision

Anoop Cherian, Suvrit Sra, 2016 .

Kronecker Determinantal Point Processes

Suvrit Sra, Zelda Mariet, 2016, NIPS.

Tackling Box-Constrained Optimization via a New Projected Quasi-Newton Approach

Inderjit S. Dhillon, Suvrit Sra, Dongmin Kim, 2010, SIAM J. Sci. Comput..

Fast projections onto mixed-norm balls with applications

Suvrit Sra, 2012, Data Mining and Knowledge Discovery.

Fixed-point algorithms for determinantal point processes pdf

Suvrit Sra, Zelda Mariet, 2015, ArXiv.

Generalized Dictionary Learning for Symmetric Positive Definite Matrices with Application to Nearest Neighbor Retrieval

Anoop Cherian, Suvrit Sra, 2011, ECML/PKDD.

Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods

Suvrit Sra, Melanie Weber, S. Sra, 2019, ArXiv.

Fast incremental method for smooth nonconvex optimization

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization

Alexander J. Smola, Barnabás Póczos, Suvrit Sra, 2016, NIPS.

On inequalities for normalized Schur functions

Suvrit Sra, 2016, Eur. J. Comb..

Gaussian quadrature for matrix inverse forms with applications

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2016, ICML.

On Convergence of Training Loss Without Reaching Stationary Points pdf

Suvrit Sra, Ali Jadbabaie, Jingzhao Zhang, 2021, ArXiv.

Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates

Suvrit Sra, Alp Yurtsever, Alex Gu, 2021 .

Three Operator Splitting with a Nonconvex Loss Function

Suvrit Sra, Alp Yurtsever, Varun Mangalick, 2021, ICML.

Positive definite functions of noncommuting contractions, Hua-Bellman matrices, and a new distance metric

Suvrit Sra, 2021 .

Online Learning in Unknown Markov Games

Suvrit Sra, Yi Tian, Yuanhao Wang, 2021, ICML.

Can contrastive learning avoid shortcut solutions? pdf

Suvrit Sra, Joshua Robinson, Stefanie Jegelka, 2021, NeurIPS.

A Riemannian Accelerated Proximal Extragradient Framework and its Implications pdf

Suvrit Sra, Jikai Jin, S. Sra, 2021, ArXiv.

Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? pdf

Suvrit Sra, Ali Jadbabaie, Chulhee Yun, 2021, COLT.

Coping with Label Shift via Distributionally Robust Optimisation pdf

Suvrit Sra, Andreas Veit, Jingzhao Zhang, 2020, ICLR.

Introducing Discrepancy Values of Matrices and their Application to Bounding Norms of Commutators

Suvrit Sra, Pourya Habib Zadeh, 2021 .

Max-Margin Contrastive Learning pdf

Anoop Cherian, Suvrit Sra, Rama Chellappa, 2021, ArXiv.

Time Varying Regression with Hidden Linear Dynamics

Devavrat Shah, Suvrit Sra, Horia Mania, 2021, L4DC.

Provably Efficient Algorithms for Multi-Objective Competitive RL

Suvrit Sra, Tiancheng Yu, Jingzhao Zhang, 2021, ICML.

Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond pdf

Suvrit Sra, Shashank Rajput, Chulhee Yun, 2021, ArXiv.

Text Clustering with Mixture of von Mises-Fisher Distributions

Inderjit S. Dhillon, Suvrit Sra, I. Dhillon, 2009 .

Completely strong superadditivity of generalized matrix functions

Suvrit Sra, Minghua Lin, 2014 .

Online blind deconvolution for astronomical imaging

Suvrit Sra, Michael Hirsch, Stefan Harmeling, 2009, 2009 IEEE International Conference on Computational Photography (ICCP).

Online Multi-frame Blind Deconvolution with Super-resolution and Saturation Correction

Bernhard Schölkopf, Suvrit Sra, Michael Hirsch, 2011 .

Expectation Maximization for Clustering on Hyperspheres

Inderjit S. Dhillon, Suvrit Sra, Arindam Banerjee, 2003 .

Column Subset Selection via Polynomial Time Dual Volume Sampling

Suvrit Sra, Stefanie Jegelka, Chengtao Li, 2017 .

The Metric Nearness Problem with Applications

Inderjit S. Dhillon, Suvrit Sra, Joel A. Tropp, 2003 .

Portfolio Optimization with Groupwise Selection

Suvrit Sra, Namhyoung Kim, S. Sra, 2014 .

Correlation matrix nearness and completion under observation uncertainty

Suvrit Sra, Carlos M. Alaíz, Francesco Dinuzzo, 2015 .

Logarithmic inequalities under a symmetric polynomial dominance order

Suvrit Sra, 2018, Proceedings of the American Mathematical Society.

Statistical inference with the Elliptical Gamma Distribution

Matthias Bethge, Suvrit Sra, Reshad Hosseini, 2014 .