Suvrit Sra

ORCID

Publication Activity (10 Years)

Years Active: 2003-2024
Publications (10 Years): 161

Top Venues

Publications

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)
Xiang Cheng, Jingzhao Zhang, Suvrit Sra
Efficient Sampling on Riemannian Manifolds via Langevin MCMC. CoRR (2024)
Guy Kornowski, Swati Padmanabhan, Kai Wang, Zhe Zhang, Suvrit Sra
First-Order Methods for Linearly Constrained Bilevel Optimization. CoRR (2024)
Sanchayan Dutta, Xiang Cheng, Suvrit Sra
Riemannian Bilevel Optimization. CoRR (2024)
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)
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)
Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand, Suvrit Sra
Transformers learn to implement preconditioned gradient descent for in-context learning. CoRR (2023)
Melanie Weber, Suvrit Sra
Riemannian Optimization via Frank-Wolfe Methods. Math. Program. 199 (1) (2023)
David Xing Wu, Chulhee Yun, Suvrit Sra
On the Training Instability of Shuffling SGD with Batch Normalization. ICML (2023)
David X. Wu, Chulhee Yun, Suvrit Sra
On the Training Instability of Shuffling SGD with Batch Normalization. CoRR (2023)
Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra
Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control? L4DC (2023)
Melanie Weber, Suvrit Sra
Global optimality for Euclidean CCCP under Riemannian convexity. ICML (2023)
Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand, Suvrit Sra
Transformers learn to implement preconditioned gradient descent for in-context learning. NeurIPS (2023)
Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra
How to escape sharp minima. CoRR (2023)
Xiang Cheng, Yuxin Chen, Suvrit Sra
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context. CoRR (2023)
Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra
Linear attention is (maybe) all you need (to understand transformer optimization). CoRR (2023)
Peiyuan Zhang, Jingzhao Zhang, Suvrit Sra
Sion's Minimax Theorem in Geodesic Metric Spaces and a Riemannian Extragradient Algorithm. SIAM J. Optim. 33 (4) (2023)
Yan Dai, Kwangjun Ahn, Suvrit Sra
The Crucial Role of Normalization in Sharpness-Aware Minimization. CoRR (2023)
Yan Dai, Kwangjun Ahn, Suvrit Sra
The Crucial Role of Normalization in Sharpness-Aware Minimization. NeurIPS (2023)
Adarsh Barik, Suvrit Sra, Jean Honorio
Invex Programs: First Order Algorithms and Their Convergence. CoRR (2023)
Chulhee Yun, Shashank Rajput, Suvrit Sra
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. ICLR (2022)
Peiyuan Zhang, Jingzhao Zhang, Suvrit Sra
Minimax in Geodesic Metric Spaces: Sion's Theorem and Algorithms. CoRR (2022)
Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra
Understanding the unstable convergence of gradient descent. CoRR (2022)
Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra
Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control? CoRR (2022)
Suvrit Sra, Melanie Weber
On a class of geodesically convex optimization problems solved via Euclidean MM methods. CoRR (2022)
Xiang Cheng, Jingzhao Zhang, Suvrit Sra
Efficient Sampling on Riemannian Manifolds via Langevin MCMC. NeurIPS (2022)
Kwangjun Ahn, Suvrit Sra
Understanding Nesterov's Acceleration via Proximal Point Method. SOSA (2022)
Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra
Understanding the unstable convergence of gradient descent. ICML (2022)
Melanie Weber, Suvrit Sra
Computing Brascamp-Lieb Constants through the lens of Thompson Geometry. CoRR (2022)
Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie
Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity. ICML (2022)
Alp Yurtsever, Suvrit Sra
CCCP is Frank-Wolfe in disguise. NeurIPS (2022)
Horia Mania, Ali Jadbabaie, Devavrat Shah, Suvrit Sra
Time Varying Regression with Hidden Linear Dynamics. L4DC (2022)
Anshul Shah, Suvrit Sra, Rama Chellappa, Anoop Cherian
Max-Margin Contrastive Learning. AAAI (2022)
Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective. ICML (2022)
Derek Lim, Joshua Robinson, Lingxiao Zhao, Tess Smidt, Suvrit Sra, Haggai Maron, Stefanie Jegelka
Sign and Basis Invariant Networks for Spectral Graph Representation Learning. CoRR (2022)
Jikai Jin, Suvrit Sra
Understanding Riemannian Acceleration via a Proximal Extragradient Framework. COLT (2022)
Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra
Can contrastive learning avoid shortcut solutions? NeurIPS (2021)
Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie
On Convergence of Training Loss Without Reaching Stationary Points. CoRR (2021)
Tiancheng Yu, Yi Tian, Jingzhao Zhang, Suvrit Sra
Provably Efficient Algorithms for Multi-Objective Competitive RL. ICML (2021)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? COLT (2021)
Tiancheng Yu, Yi Tian, Jingzhao Zhang, Suvrit Sra
Provably Efficient Algorithms for Multi-Objective Competitive RL. CoRR (2021)
Alp Yurtsever, Varun Mangalick, Suvrit Sra
Three Operator Splitting with a Nonconvex Loss Function. ICML (2021)
Yi Tian, Yuanhao Wang, Tiancheng Yu, Suvrit Sra
Online Learning in Unknown Markov Games. ICML (2021)
Alp Yurtsever, Alex Gu, Suvrit Sra
Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates. NeurIPS (2021)
Joshua David Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka
Contrastive Learning with Hard Negative Samples. ICLR (2021)
Chulhee Yun, Shashank Rajput, Suvrit Sra
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. CoRR (2021)
Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra
Coping with Label Shift via Distributionally Robust Optimisation. ICLR (2021)
Anshul Shah, Suvrit Sra, Rama Chellappa, Anoop Cherian
Max-Margin Contrastive Learning. CoRR (2021)
Jikai Jin, Suvrit Sra
A Riemannian Accelerated Proximal Extragradient Framework and its Implications. CoRR (2021)
Joshua Robinson, Li Sun, Ke Yu, Kayhan Batmanghelich, Stefanie Jegelka, Suvrit Sra
Can contrastive learning avoid shortcut solutions? CoRR (2021)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? CoRR (2021)
Joshua Robinson, Stefanie Jegelka, Suvrit Sra
Strength from Weakness: Fast Learning Using Weak Supervision. CoRR (2020)
Chi Jin, Tiancheng Jin, Haipeng Luo, Suvrit Sra, Tiancheng Yu
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition. ICML (2020)
Florian Yger, Sylvain Chevallier, Quentin Barthélemy, Suvrit Sra
Geodesically-convex optimization for averaging partially observed covariance matrices. ACML (2020)
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)
Jingzhao Zhang, Hongzhou Lin, Suvrit Sra, Ali Jadbabaie
On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions. CoRR (2020)
Yi Tian, Jian Qian, Suvrit Sra
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes. CoRR (2020)
Jingzhao Zhang, Tianxing He, Suvrit Sra, Ali Jadbabaie
Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity. ICLR (2020)
Yi Tian, Yuanhao Wang, Tiancheng Yu, Suvrit Sra
Provably Efficient Online Agnostic Learning in Markov Games. CoRR (2020)
Yi Tian, Jian Qian, Suvrit Sra
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes. NeurIPS (2020)
Horia Mania, Suvrit Sra
Why do classifier accuracies show linear trends under distribution shift? CoRR (2020)
Reshad Hosseini, Suvrit Sra
An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization. Math. Program. 181 (1) (2020)
Kwangjun Ahn, Suvrit Sra
From Nesterov's Estimate Sequence to Riemannian Acceleration. COLT (2020)
Joshua Robinson, Stefanie Jegelka, Suvrit Sra
Strength from Weakness: Fast Learning Using Weak Supervision. ICML (2020)
Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie
Stochastic Optimization with Non-stationary Noise. CoRR (2020)
Jingzhao Zhang, Aditya Krishna Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra
Coping with Label Shift via Distributionally Robust Optimisation. CoRR (2020)
Joshua Robinson, Ching-Yao Chuang, Suvrit Sra, Stefanie Jegelka
Contrastive Learning with Hard Negative Samples. CoRR (2020)
Kwangjun Ahn, Suvrit Sra
On Tight Convergence Rates of Without-replacement SGD. CoRR (2020)
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 (2020)
Kwangjun Ahn, Chulhee Yun, Suvrit Sra
SGD with shuffling: optimal rates without component convexity and large epoch requirements. NeurIPS (2020)
Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Suvrit Sra, Ali Jadbabaie
Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions. ICML (2020)
Joshua Robinson, Suvrit Sra, Stefanie Jegelka
Flexible Modeling of Diversity with Strongly Log-Concave Distributions. NeurIPS (2019)
Jingzhao Zhang, Tianxing He, Suvrit Sra, Ali Jadbabaie
Analysis of Gradient Clipping and Adaptive Scaling with a Relaxed Smoothness Condition. CoRR (2019)
Matthew Staib, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar, Suvrit Sra
Escaping Saddle Points with Adaptive Gradient Methods. CoRR (2019)
Alp Yurtsever, Suvrit Sra, Volkan Cevher
Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator. ICML (2019)
Suvrit Sra
Metrics Induced by Quantum Jensen-Shannon-Renyí and Related Divergences. CoRR (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Are deep ResNets provably better than linear predictors? NeurIPS (2019)
Joshua Robinson, Suvrit Sra, Stefanie Jegelka
Flexible Modeling of Diversity with Strongly Log-Concave Distributions. CoRR (2019)
Melanie Weber, Suvrit Sra
Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods. CoRR (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Are deep ResNets provably better than linear predictors? CoRR (2019)
Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank J. Reddi, Sanjiv Kumar, Suvrit Sra
Why ADAM Beats SGD for Attention Models. CoRR (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Small nonlinearities in activation functions create bad local minima in neural networks. ICLR (Poster) (2019)
Jeff Z. HaoChen, Suvrit Sra
Random Shuffling Beats SGD after Finite Epochs. ICML (2019)
Jingzhao Zhang, Suvrit Sra, Ali Jadbabaie
Acceleration in First Order Quasi-strongly Convex Optimization by ODE Discretization. CDC (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity. NeurIPS (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Efficiently testing local optimality and escaping saddles for ReLU networks. ICLR (Poster) (2019)
Zelda Mariet, Mike Gartrell, Suvrit Sra
Learning Determinantal Point Processes by Corrective Negative Sampling. AISTATS (2019)
Matthew Staib, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar, Suvrit Sra
Escaping Saddle Points with Adaptive Gradient Methods. ICML (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Efficiently testing local optimality and escaping saddles for ReLU networks. CoRR (2018)
Chengtao Li, David Alvarez-Melis, Keyulu Xu, Stefanie Jegelka, Suvrit Sra
Distributional Adversarial Networks. ICLR (Workshop) (2018)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
A Critical View of Global Optimality in Deep Learning. CoRR (2018)
Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie
Direct Runge-Kutta Discretization Achieves Acceleration. CoRR (2018)
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)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Finite sample expressive power of small-width ReLU networks. CoRR (2018)
Suvrit Sra, Nisheeth K. Vishnoi, Ozan Yildiz
On Geodesically Convex Formulations for the Brascamp-Lieb Constant. APPROX-RANDOM (2018)
Álvaro Barbero Jiménez, Suvrit Sra
Modular Proximal Optimization for Multidimensional Total-Variation Regularization. J. Mach. Learn. Res. 19 (2018)
Zelda Mariet, Mike Gartrell, Suvrit Sra
Learning Determinantal Point Processes by Sampling Inferred Negatives. CoRR (2018)
Jingzhao Zhang, Hongyi Zhang, Suvrit Sra
R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate. CoRR (2018)
Zelda E. Mariet, Suvrit Sra, Stefanie Jegelka
Exponentiated Strongly Rayleigh Distributions. NeurIPS (2018)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Global Optimality Conditions for Deep Neural Networks. ICLR (Poster) (2018)

Suvrit Sra.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Suvrit Sra