Suvrit Sra
97 publications
18 venues
H Index 39
Affiliation
Massachusetts Institute of Technology (MIT), Laboratory for Information and Decision Systems, Cambridge, MA, USAMax Planck Institute for Biological Cybernetics, T bingen, Germany
University of Texas at Austin, Department of Computer Sciences, Austin, TX, USA
Links
DBLPGoogle Scholar
Twitter- https://optml.mit.edu/index.html
- https://openreview.net/profile?id=~Suvrit_Sra1
- https://zbmath.org/authors/?q=ai:sra.suvrit
- https://mathscinet.ams.org/mathscinet/MRAuthorID/815361
- https://mathgenealogy.org/id.php?id=157578
- https://orcid.org/0000-0001-8516-4925
- https://www.wikidata.org/entity/Q56589650
- https://id.loc.gov/authorities/names/n2011009067
- https://d-nb.info/gnd/1017466106
| Name | Venue | Year | citations |
|---|---|---|---|
Graph Transformers Dream of Electric Flow.
|
ICLR | 2025 | 0 |
| First-Order Methods for Linearly Constrained Bilevel Optimization.
|
NIPS/NeurIPS | 2024 | 13 |
| How to Escape Sharp Minima with Random Perturbations.
|
ICML | 2024 | 0 |
| Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context.
|
ICML | 2024 | 0 |
| Linear attention is (maybe) all you need (to understand Transformer optimization).
|
ICLR | 2024 | 0 |
| Transformers learn to implement preconditioned gradient descent for in-context learning.
|
NIPS/NeurIPS | 2023 | 260 |
| On the Training Instability of Shuffling SGD with Batch Normalization.
|
ICML | 2023 | 6 |
| The Crucial Role of Normalization in Sharpness-Aware Minimization.
|
NIPS/NeurIPS | 2023 | 30 |
| Global optimality for Euclidean CCCP under Riemannian convexity.
|
ICML | 2023 | 8 |
| Sign and Basis Invariant Networks for Spectral Graph Representation Learning.
|
ICLR | 2023 | 0 |
| Efficient Sampling on Riemannian Manifolds via Langevin MCMC.
|
NIPS/NeurIPS | 2022 | 0 |
| Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond.
|
ICLR | 2022 | 0 |
| Understanding the unstable convergence of gradient descent.
|
ICML | 2022 | 81 |
| CCCP is Frank-Wolfe in disguise.
|
NIPS/NeurIPS | 2022 | 19 |
| Max-Margin Contrastive Learning.
|
AAAI | 2022 | 0 |
| Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity.
|
ICML | 2022 | 0 |
| Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective.
|
ICML | 2022 | 0 |
| Understanding Riemannian Acceleration via a Proximal Extragradient Framework.
|
COLT | 2022 | 0 |
| Three Operator Splitting with a Nonconvex Loss Function.
|
ICML | 2021 | 13 |
| Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates.
|
NIPS/NeurIPS | 2021 | 12 |
| Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?
|
COLT | 2021 | 13 |
| Provably Efficient Algorithms for Multi-Objective Competitive RL.
|
ICML | 2021 | 24 |
| Can contrastive learning avoid shortcut solutions?
|
NIPS/NeurIPS | 2021 | 164 |
| Online Learning in Unknown Markov Games.
|
ICML | 2021 | 46 |
| Coping with Label Shift via Distributionally Robust Optimisation.
|
ICLR | 2021 | 0 |
| Contrastive Learning with Hard Negative Samples.
|
ICLR | 2021 | 0 |
| Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes.
|
NIPS/NeurIPS | 2020 | 27 |
| Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions.
|
ICML | 2020 | 90 |
| Strength from Weakness: Fast Learning Using Weak Supervision.
|
ICML | 2020 | 35 |
| From Nesterov's Estimate Sequence to Riemannian Acceleration.
|
COLT | 2020 | 85 |
| Geodesically-convex optimization for averaging partially observed covariance matrices.
|
ACML | 2020 | 3 |
| Why are Adaptive Methods Good for Attention Models?
|
NIPS/NeurIPS | 2020 | 345 |
| SGD with shuffling: optimal rates without component convexity and large epoch requirements.
|
NIPS/NeurIPS | 2020 | 70 |
| Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition.
|
ICML | 2020 | 0 |
| Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity.
|
ICLR | 2020 | 0 |
| Are deep ResNets provably better than linear predictors?
|
NIPS/NeurIPS | 2019 | 14 |
| Escaping Saddle Points with Adaptive Gradient Methods.
|
ICML | 2019 | 78 |
| Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator.
|
ICML | 2019 | 51 |
| Flexible Modeling of Diversity with Strongly Log-Concave Distributions.
|
NIPS/NeurIPS | 2019 | 12 |
| Random Shuffling Beats SGD after Finite Epochs.
|
ICML | 2019 | 0 |
| Learning Determinantal Point Processes by Corrective Negative Sampling.
|
AISTATS | 2019 | 0 |
| Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity.
|
NIPS/NeurIPS | 2019 | 0 |
| Non-Linear Temporal Subspace Representations for Activity Recognition.
|
CVPR | 2018 | 45 |
| An Estimate Sequence for Geodesically Convex Optimization.
|
COLT | 2018 | 63 |
| Direct Runge-Kutta Discretization Achieves Acceleration.
|
NIPS/NeurIPS | 2018 | 112 |
| Exponentiated Strongly Rayleigh Distributions.
|
NIPS/NeurIPS | 2018 | 14 |
| A Generic Approach for Escaping Saddle points.
|
AISTATS | 2018 | 0 |
| Modular Proximal Optimization for Multidimensional Total-Variation Regularization.
|
JMLR | 2018 | 0 |
| Elementary Symmetric Polynomials for Optimal Experimental Design.
|
NIPS/NeurIPS | 2017 | 20 |
| Polynomial time algorithms for dual volume sampling.
|
NIPS/NeurIPS | 2017 | 31 |
| Combinatorial Topic Models using Small-Variance Asymptotics.
|
AISTATS | 2017 | 0 |
| Fast DPP Sampling for Nystrom with Application to Kernel Methods.
|
ICML | 2016 | 76 |
| Kronecker Determinantal Point Processes.
|
NIPS/NeurIPS | 2016 | 32 |
| Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization.
|
NIPS/NeurIPS | 2016 | 202 |
| First-order Methods for Geodesically Convex Optimization.
|
COLT | 2016 | 320 |
| AdaDelay: Delay Adaptive Distributed Stochastic Optimization.
|
AISTATS | 2016 | 45 |
| Geometric Mean Metric Learning.
|
ICML | 2016 | 178 |
| Stochastic Variance Reduction for Nonconvex Optimization.
|
ICML | 2016 | 642 |
| Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling.
|
NIPS/NeurIPS | 2016 | 39 |
| Gaussian quadrature for matrix inverse forms with applications.
|
ICML | 2016 | 0 |
| Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms.
|
ICML | 2016 | 0 |
| Efficient Sampling for k-Determinantal Point Processes.
|
AISTATS | 2016 | 0 |
| Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds.
|
NIPS/NeurIPS | 2016 | 0 |
| Fixed-point algorithms for learning determinantal point processes.
|
ICML | 2015 | 55 |
| On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants.
|
NIPS/NeurIPS | 2015 | 199 |
| Matrix Manifold Optimization for Gaussian Mixtures.
|
NIPS/NeurIPS | 2015 | 97 |
| Data modeling with the elliptical gamma distribution.
|
AISTATS | 2015 | 6 |
| Large-scale randomized-coordinate descent methods with non-separable linear constraints.
|
UAI | 2015 | 0 |
| Fast Newton methods for the group fused lasso.
|
UAI | 2014 | 17 |
| Efficient Structured Matrix Rank Minimization.
|
NIPS/NeurIPS | 2014 | 20 |
| Towards an optimal stochastic alternating direction method of multipliers.
|
ICML | 2014 | 59 |
| Riemannian Sparse Coding for Positive Definite Matrices.
|
ECCV | 2014 | 55 |
| Randomized Nonlinear Component Analysis.
|
ICML | 2014 | 183 |
| Geometric optimisation on positive definite matrices for elliptically contoured distributions.
|
NIPS/NeurIPS | 2013 | 30 |
| Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices.
|
TPAMI | 2013 | 180 |
| Reflection methods for user-friendly submodular optimization.
|
NIPS/NeurIPS | 2013 | 80 |
| Fast projections onto mixed-norm balls with applications.
|
DMKD | 2012 | 29 |
| A new metric on the manifold of kernel matrices with application to matrix geometric means.
|
NIPS/NeurIPS | 2012 | 155 |
| Scalable nonconvex inexact proximal splitting.
|
NIPS/NeurIPS | 2012 | 69 |
| Generalized Dictionary Learning for Symmetric Positive Definite Matrices with Application to Nearest Neighbor Retrieval.
|
ECML/PKDD | 2011 | 50 |
| Fast Newton-type Methods for Total Variation Regularization.
|
ICML | 2011 | 94 |
| Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence.
|
ICCV | 2011 | 85 |
| Fast Projections onto ℓ1, q -Norm Balls for Grouped Feature Selection.
|
ECML/PKDD | 2011 | 39 |
| Efficient filter flow for space-variant multiframe blind deconvolution.
|
CVPR | 2010 | 265 |
| A scalable trust-region algorithm with application to mixed-norm regression.
|
ICML | 2010 | 40 |
| Workshop summary: Numerical mathematics in machine learning.
|
ICML | 2009 | 0 |
| Convex Perturbations for Scalable Semidefinite Programming.
|
AISTATS | 2009 | 9 |
| Block-Iterative Algorithms for Non-negative Matrix Approximation.
|
ICDM | 2008 | 5 |
| Fast Newton-type Methods for the Least Squares Nonnegative Matrix Approximation Problem.
|
SDM | 2007 | 145 |
| Information-theoretic metric learning.
|
ICML | 2007 | 0 |
| Efficient Large Scale Linear Programming Support Vector Machines.
|
ECML/PKDD | 2006 | 20 |
| Incremental Aspect Models for Mining Document Streams.
|
ECML/PKDD | 2006 | 19 |
| Generalized Nonnegative Matrix Approximations with Bregman Divergences.
|
NIPS/NeurIPS | 2005 | 522 |
| Clustering on the Unit Hypersphere using von Mises-Fisher Distributions.
|
JMLR | 2005 | 1034 |
| Triangle Fixing Algorithms for the Metric Nearness Problem.
|
NIPS/NeurIPS | 2004 | 23 |
| Minimum Sum-Squared Residue Co-Clustering of Gene Expression Data.
|
SDM | 2004 | 329 |
| Generative model-based clustering of directional data.
|
KDD | 2003 | 123 |