Sujay Sanghavi

research

∙ 07/31/2023

Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity

While deep learning (DL) models are state-of-the-art in text and image d...

0 Charlie Hou, et al. ∙

research

∙ 06/15/2023

Logarithmic Bayes Regret Bounds

We derive the first finite-time logarithmic regret bounds for Bayesian b...

0 Alexia Atsidakou, et al. ∙

research

∙ 01/30/2023

Understanding Self-Distillation in the Presence of Label Noise

Self-distillation (SD) is the process of first training a teacher model ...

0 Rudrajit Das, et al. ∙

research

∙ 12/17/2022

Latent Variable Representation for Reinforcement Learning

Deep latent variable models have achieved significant empirical successe...

10 Tongzheng Ren, et al. ∙

research

∙ 11/15/2022

Bayesian Fixed-Budget Best-Arm Identification

Fixed-budget best-arm identification (BAI) is a bandit problem where the...

0 Alexia Atsidakou, et al. ∙

research

∙ 09/19/2022

Toward Understanding Privileged Features Distillation in Learning-to-Rank

In learning-to-rank problems, a privileged feature is one that is availa...

0 Shuo Yang, et al. ∙

research

∙ 08/11/2022

On the Value of Behavioral Representations for Dense Retrieval

We consider text retrieval within dense representational space in real-w...

0 Nan Jiang, et al. ∙

research

∙ 05/23/2022

Beyond EM Algorithm on Over-specified Two-Component Location-Scale Gaussian Mixtures

The Expectation-Maximization (EM) algorithm has been predominantly used ...

5 Tongzheng Ren, et al. ∙

research

∙ 05/16/2022

An Exponentially Increasing Step-size for Parameter Estimation in Statistical Models

Using gradient descent (GD) with fixed or decaying step-size is standard...

12 Nhat Ho, et al. ∙

research

∙ 03/23/2022

Minimax Regret for Cascading Bandits

Cascading bandits model the task of learning to rank K out of L items ov...

0 Daniel Vial, et al. ∙

research

∙ 02/24/2022

Sample Efficiency of Data Augmentation Consistency Regularization

Data augmentation is popular in the training of large neural networks; c...

7 Shuo Yang, et al. ∙

research

∙ 02/09/2022

Improving Computational Complexity in Statistical Models with Second-Order Information

It is known that when the statistical models are singular, i.e., the Fis...

14 Tongzheng Ren, et al. ∙

research

∙ 10/15/2021

Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent

We study the statistical and computational complexities of the Polyak st...

0 Tongzheng Ren, et al. ∙

research

∙ 06/16/2021

Robust Training in High Dimensions via Block Coordinate Geometric Median Descent

Geometric median (Gm) is a classical method in statistics for achieving ...

12 Anish Acharya, et al. ∙

research

∙ 06/13/2021

DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning

In this paper, we focus on facilitating differentially private quantized...

20 Rudrajit Das, et al. ∙

research

∙ 06/01/2021

Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification

Extreme multi-label classification (XMC) aims to learn a model that can ...

26 Tavor Z. Baharav, et al. ∙

research

∙ 03/25/2021

Nearly Horizon-Free Offline Reinforcement Learning

We revisit offline reinforcement learning on episodic time-homogeneous t...

0 Tongzheng Ren, et al. ∙

research

∙ 03/03/2021

Combinatorial Bandits without Total Order for Arms

We consider the combinatorial bandits problem, where at each time step, ...

5 Shuo Yang, et al. ∙

research

∙ 03/03/2021

Linear Bandit Algorithms with Sublinear Time Complexity

We propose to accelerate existing linear bandit algorithms to achieve pe...

18 Shuo Yang, et al. ∙

research

∙ 12/07/2020

Improved Convergence Rates for Non-Convex Federated Learning with Compression

Federated learning is a new distributed learning paradigm that enables e...

14 Rudrajit Das, et al. ∙

research

∙ 11/28/2020

On Generalization of Adaptive Methods for Over-parameterized Linear Regression

Over-parameterization and adaptive methods have played a crucial role in...

0 Vatsal Shah, et al. ∙

research

∙ 11/20/2020

On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization

In decentralized optimization, it is common algorithmic practice to have...

2 Abolfazl Hashemi, et al. ∙

research

∙ 04/01/2020

Extreme Multi-label Classification from Aggregated Labels

Extreme multi-label classification (XMC) is the problem of finding the r...

7 Yanyao Shen, et al. ∙

research

∙ 01/10/2020

Choosing the Sample with Lowest Loss makes SGD Robust

The presence of outliers can potentially significantly skew the paramete...

42 Vatsal Shah, et al. ∙

research

∙ 11/08/2019

Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space

Quadratic regression involves modeling the response as a (generalized) l...

0 Shuo Yang, et al. ∙

research

∙ 09/04/2019

Learning Distributions Generated by One-Layer ReLU Networks

We consider the problem of estimating the parameters of a d-dimensional ...

22 Shanshan Wu, et al. ∙

research

∙ 07/27/2019

Blocking Bandits

We consider a novel stochastic multi-armed bandit setting, where playing...

0 Soumya Basu, et al. ∙

research

∙ 02/10/2019

Iterative Least Trimmed Squares for Mixed Linear Regression

Given a linear regression setting, Iterative Least Trimmed Squares (ILTS...

0 Yanyao Shen, et al. ∙

research

∙ 11/16/2018

Minimum norm solutions do not always generalize well for over-parameterized problems

Stochastic gradient descent is the de facto algorithm for training deep ...

0 Vatsal Shah, et al. ∙

research

∙ 10/28/2018

Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models

We characterize the effectiveness of a natural and classic algorithm for...

6 Shanshan Wu, et al. ∙

research

∙ 10/28/2018

Iteratively Learning from the Best

We study a simple generic framework to address the issue of bad training...

0 Yanyao Shen, et al. ∙

research

∙ 06/26/2018

The Sparse Recovery Autoencoder

Linear encoding of sparse vectors is widely popular, but is most commonl...

6 Shanshan Wu, et al. ∙

research

∙ 11/04/2017

Provable quantum state tomography via non-convex methods

With nowadays steadily growing quantum processors, it is required to dev...

0 Anastasios Kyrillidis, et al. ∙

research

∙ 03/08/2017

Sparse Quadratic Logistic Regression in Sub-quadratic Time

We consider support recovery in the quadratic logistic regression settin...

0 Karthikeyan Shanmugam, et al. ∙

research

∙ 10/21/2016

Single Pass PCA of Matrix Products

In this paper we present a new algorithm for computing a low rank approx...

0 Shanshan Wu, et al. ∙

research

∙ 10/04/2016

The Search Problem in Mixture Models

We consider the task of learning the parameters of a single component o...

0 Avik Ray, et al. ∙

research

∙ 09/12/2016

Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach

We consider the non-square matrix sensing problem, under restricted isom...

0 Dohyung Park, et al. ∙

research

∙ 08/19/2016

Solving a Mixture of Many Random Linear Equations by Tensor Decomposition and Alternating Minimization

We consider the problem of solving mixed random linear equations with k ...

0 Xinyang Yi, et al. ∙

research

∙ 06/04/2016

Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems

We study the projected gradient descent method on low-rank matrix proble...

0 Dohyung Park, et al. ∙

research

∙ 03/22/2016

Trading-off variance and complexity in stochastic gradient descent

Stochastic gradient descent is the method of choice for large-scale mach...

0 Vatsal Shah, et al. ∙

research

∙ 09/14/2015

Dropping Convexity for Faster Semi-definite Optimization

We study the minimization of a convex function f(X) over the set of n× n...

0 Srinadh Bhojanapalli, et al. ∙

research

∙ 06/25/2015

The local convexity of solving systems of quadratic equations

This paper considers the recovery of a rank r positive semidefinite matr...

0 Chris D. White, et al. ∙

research

∙ 06/08/2015

Convergence Rates of Active Learning for Maximum Likelihood Estimation

An active learner is given a class of models, a large set of unlabeled e...

0 Kamalika Chaudhuri, et al. ∙

research

∙ 02/17/2015

A New Sampling Technique for Tensors

In this paper we propose new techniques to sample arbitrary third-order ...

0 Srinadh Bhojanapalli, et al. ∙

research

∙ 10/31/2014

Greedy Subspace Clustering

We consider the problem of subspace clustering: given points that lie on...

0 Dohyung Park, et al. ∙

research

∙ 10/28/2014

Non-convex Robust PCA

We propose a new method for robust PCA -- the task of recovering a low-r...

0 Praneeth Netrapalli, et al. ∙

research

∙ 10/14/2014

Tighter Low-rank Approximation via Sampling the Leveraged Element

In this work, we propose a new randomized algorithm for computing a low-...

0 Srinadh Bhojanapalli, et al. ∙

research

∙ 06/12/2013

Completing Any Low-rank Matrix, Provably

Matrix completion, i.e., the exact and provable recovery of a low-rank m...

0 Yudong Chen, et al. ∙

research

∙ 06/02/2013

Phase Retrieval using Alternating Minimization

Phase retrieval problems involve solving linear equations, but with miss...

0 Praneeth Netrapalli, et al. ∙

research

∙ 12/03/2012

Low-rank Matrix Completion using Alternating Minimization

Alternating minimization represents a widely applicable and empirically ...

0 Prateek Jain, et al. ∙

Sujay Sanghavi

Featured Co-authors