Suvrit Sra

is this you? claim profile

∙ 0 followers
MIT ∙ Max Planck Society

Researcher at Massachusetts Institute of Technology (MIT), Cofounder; Chief AI Officer at macro-eyes

Contrastive Learning with Hard Negative Samples

We consider the question: how can you sample good negative examples for ...
10/09/2020 ∙ by Joshua Robinson, et al. ∙ 0 ∙ share

read it
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

We study minimax optimal reinforcement learning in episodic factored Mar...
06/24/2020 ∙ by Yi Tian, et al. ∙ 11 ∙ share

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

We study without-replacement SGD for solving finite-sum optimization pro...
06/12/2020 ∙ by Kwangjun Ahn, et al. ∙ 0 ∙ share

read it
Stochastic Optimization with Non-stationary Noise

We investigate stochastic optimization problems under relaxed assumption...
06/08/2020 ∙ by Jingzhao Zhang, et al. ∙ 0 ∙ share

read it
On Tight Convergence Rates of Without-replacement SGD

For solving finite-sum optimization problems, SGD without replacement sa...
04/18/2020 ∙ by Kwangjun Ahn, et al. ∙ 0 ∙ share

read it
Strength from Weakness: Fast Learning Using Weak Supervision

We study generalization properties of weakly supervised learning. That i...
02/19/2020 ∙ by Joshua Robinson, et al. ∙ 8 ∙ share

read it
On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions

We provide the first non-asymptotic analysis for finding stationary poin...
02/10/2020 ∙ by Jingzhao Zhang, et al. ∙ 0 ∙ share

read it
From Nesterov's Estimate Sequence to Riemannian Acceleration

We propose the first global accelerated gradient method for Riemannian m...
01/24/2020 ∙ by Kwangjun Ahn, et al. ∙ 0 ∙ share

read it
Why ADAM Beats SGD for Attention Models

While stochastic gradient descent (SGD) is still the de facto algorithm ...
12/06/2019 ∙ by Jingzhao Zhang, et al. ∙ 0 ∙ share

read it
Metrics Induced by Quantum Jensen-Shannon-Renyí and Related Divergences

We study symmetric divergences on Hermitian positive definite matrices g...
11/06/2019 ∙ by Suvrit Sra, et al. ∙ 0 ∙ share

read it
Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods

We study stochastic projection-free methods for constrained optimization...
10/09/2019 ∙ by Melanie Weber, et al. ∙ 0 ∙ share

read it
Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation

A Markov Decision Process (MDP) is a popular model for reinforcement lea...
07/22/2019 ∙ by Tiancheng Yu, et al. ∙ 4 ∙ share

read it
Are deep ResNets provably better than linear predictors?

Recently, a residual network (ResNet) with a single residual block has b...
07/09/2019 ∙ by Chulhee Yun, et al. ∙ 2 ∙ share

read it
Near Optimal Stratified Sampling

The performance of a machine learning system is usually evaluated by usi...
06/26/2019 ∙ by Tiancheng Yu, et al. ∙ 6 ∙ share

read it
Flexible Modeling of Diversity with Strongly Log-Concave Distributions

Strongly log-concave (SLC) distributions are a rich class of discrete pr...
06/12/2019 ∙ by Joshua Robinson, et al. ∙ 4 ∙ share

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

We provide a theoretical explanation for the fast convergence of gradien...
05/28/2019 ∙ by Jingzhao Zhang, et al. ∙ 0 ∙ share

read it
Escaping Saddle Points with Adaptive Gradient Methods

Adaptive methods such as Adam and RMSProp are widely used in deep learni...
01/26/2019 ∙ by Matthew Staib, et al. ∙ 0 ∙ share

read it
Deep-RBF Networks Revisited: Robust Classification with Rejection

One of the main drawbacks of deep neural networks, like many other class...
12/07/2018 ∙ by Pourya Habib Zadeh, et al. ∙ 0 ∙ share

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

We study smooth stochastic optimization problems on Riemannian manifolds...
11/10/2018 ∙ by Jingzhao Zhang, et al. ∙ 0 ∙ share

read it
Finite sample expressive power of small-width ReLU networks

We study universal finite sample expressivity of neural networks, define...
10/17/2018 ∙ by Chulhee Yun, et al. ∙ 12 ∙ share

read it
Efficiently testing local optimality and escaping saddles for ReLU networks

We provide a theoretical algorithm for checking local optimality and esc...
09/28/2018 ∙ by Chulhee Yun, et al. ∙ 18 ∙ share

read it
Random Shuffling Beats SGD after Finite Epochs

A long-standing problem in the theory of stochastic gradient descent (SG...
06/26/2018 ∙ by Jeff Z. HaoChen, et al. ∙ 0 ∙ share

read it
Towards Riemannian Accelerated Gradient Methods

We propose a Riemannian version of Nesterov's Accelerated Gradient algor...
06/07/2018 ∙ by Hongyi Zhang, et al. ∙ 0 ∙ share

read it
Direct Runge-Kutta Discretization Achieves Acceleration

We study gradient-based optimization methods obtained by directly discre...
05/01/2018 ∙ by Jingzhao Zhang, et al. ∙ 0 ∙ share

read it
Non-Linear Temporal Subspace Representations for Activity Recognition

Representations that can compactly and effectively capture the temporal ...
03/27/2018 ∙ by Anoop Cherian, et al. ∙ 0 ∙ share

read it
Learning Determinantal Point Processes by Sampling Inferred Negatives

Determinantal Point Processes (DPPs) have attracted significant interest...
02/15/2018 ∙ by Zelda Mariet, et al. ∙ 0 ∙ share

read it
A Critical View of Global Optimality in Deep Learning

We investigate the loss surface of deep linear and nonlinear neural netw...
02/10/2018 ∙ by Chulhee Yun, et al. ∙ 0 ∙ share

read it
A Generic Approach for Escaping Saddle points

A central challenge to using first-order methods for optimizing nonconve...
09/05/2017 ∙ by Sashank J Reddi, et al. ∙ 0 ∙ share

read it
Unsupervised robust nonparametric learning of hidden community properties

We consider learning of fundamental properties of communities in large n...
07/11/2017 ∙ by Mikhail A. Langovoy, et al. ∙ 0 ∙ share

read it
Global optimality conditions for deep neural networks

We study the error landscape of deep linear and nonlinear neural network...
07/08/2017 ∙ by Chulhee Yun, et al. ∙ 0 ∙ share

read it
An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization

We consider maximum likelihood estimation for Gaussian Mixture Models (G...
06/10/2017 ∙ by Reshad Hosseini, et al. ∙ 0 ∙ share

read it
Sequence Summarization Using Order-constrained Kernelized Feature Subspaces

Representations that can compactly and effectively capture temporal evol...
05/24/2017 ∙ by Anoop Cherian, et al. ∙ 0 ∙ share

read it
Polynomial Time Algorithms for Dual Volume Sampling

We study dual volume sampling, a method for selecting k columns from an ...
03/08/2017 ∙ by Chengtao Li, et al. ∙ 0 ∙ share

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

We study probability measures induced by set functions with constraints....
08/02/2016 ∙ by Chengtao Li, et al. ∙ 0 ∙ share

read it
Stochastic Frank-Wolfe Methods for Nonconvex Optimization

We study Frank-Wolfe methods for nonconvex stochastic and finite-sum opt...
07/27/2016 ∙ by Sashank J Reddi, et al. ∙ 0 ∙ share

read it
Geometric Mean Metric Learning

We revisit the task of learning a Euclidean metric from data. We approac...
07/18/2016 ∙ by Pourya Habib Zadeh, et al. ∙ 0 ∙ share

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

In this note we consider sampling from (non-homogeneous) strongly Raylei...
07/13/2016 ∙ by Chengtao Li, et al. ∙ 0 ∙ share

read it
Kronecker Determinantal Point Processes

Determinantal Point Processes (DPPs) are probabilistic models over all s...
05/26/2016 ∙ by Zelda Mariet, et al. ∙ 0 ∙ share

read it
Fast Stochastic Methods for Nonsmooth Nonconvex Optimization

We analyze stochastic algorithms for optimizing nonconvex, nonsmooth fin...
05/23/2016 ∙ by Sashank J Reddi, et al. ∙ 0 ∙ share

read it
Directional Statistics in Machine Learning: a Brief Review

The modern data analyst must cope with data encoded in various forms, ve...
05/01/2016 ∙ by Suvrit Sra, et al. ∙ 0 ∙ share

read it
Combinatorial Topic Models using Small-Variance Asymptotics

Topic models have emerged as fundamental tools in unsupervised machine l...
04/07/2016 ∙ by Ke Jiang, et al. ∙ 0 ∙ share

read it
Stochastic Variance Reduction for Nonconvex Optimization

We study nonconvex finite-sum problems and analyze stochastic variance r...
03/19/2016 ∙ by Sashank J Reddi, et al. ∙ 0 ∙ share

read it
Fast Incremental Method for Nonconvex Optimization

We analyze a fast incremental aggregated gradient method for optimizing ...
03/19/2016 ∙ by Sashank J Reddi, et al. ∙ 0 ∙ share

read it
First-order Methods for Geodesically Convex Optimization

Geodesic convexity generalizes the notion of (vector space) convexity to...
02/19/2016 ∙ by Hongyi Zhang, et al. ∙ 0 ∙ share

read it
Gauss quadrature for matrix inverse forms with applications

We present a framework for accelerating a spectrum of machine learning a...
12/07/2015 ∙ by Chengtao Li, et al. ∙ 0 ∙ share

read it
Diversity Networks: Neural Network Compression Using Determinantal Point Processes

We introduce Divnet, a flexible technique for learning networks with div...
11/16/2015 ∙ by Zelda Mariet, et al. ∙ 0 ∙ share

read it
AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization

We study distributed stochastic convex optimization under the delayed gr...
08/20/2015 ∙ by Suvrit Sra, et al. ∙ 0 ∙ share

read it
Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices

Data encoded as symmetric positive definite (SPD) matrices frequently ar...
07/10/2015 ∙ by Anoop Cherian, et al. ∙ 0 ∙ share

read it
Manifold Optimization for Gaussian Mixture Models

We take a new look at parameter estimation for Gaussian Mixture Models (...
06/25/2015 ∙ by Reshad Hosseini, et al. ∙ 0 ∙ share

read it
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants

We study optimization algorithms based on variance reduction for stochas...
06/23/2015 ∙ by Sashank J Reddi, et al. ∙ 0 ∙ share

read it

Suvrit Sra

Featured Co-authors