b'Raman Arora'

research

∙ 07/20/2023

From Adaptive Query Release to Machine Unlearning

We formalize the problem of machine unlearning as design of efficient un...

0 Enayat Ullah, et al. ∙

research

∙ 02/24/2023

Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards

We propose a novel offline reinforcement learning (RL) algorithm, namely...

0 Thanh Nguyen-Tang, et al. ∙

research

∙ 11/23/2022

On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation

Sample-efficient offline reinforcement learning (RL) with linear functio...

0 Thanh Nguyen-Tang, et al. ∙

research

∙ 08/19/2022

A Risk-Sensitive Approach to Policy Optimization

Standard deep reinforcement learning (DRL) aims to maximize expected rew...

7 Jared Markowitz, et al. ∙

research

∙ 06/18/2022

Adversarial Robustness is at Odds with Lazy Training

Recent works show that random neural networks are vulnerable against adv...

0 Yunjuan Wang, et al. ∙

research

∙ 06/02/2022

Faster Rates of Convergence to Stationary Points in Differentially Private Optimization

We study the problem of approximating stationary points of Lipschitz and...

0 Raman Arora, et al. ∙

research

∙ 05/06/2022

Differentially Private Generalized Linear Models Revisited

We study the problem of (ϵ,δ)-differentially private learning of linear ...

0 Raman Arora, et al. ∙

research

∙ 02/25/2021

Machine Unlearning via Algorithmic Stability

We study the problem of machine unlearning and identify a notion of algo...

0 Enayat Ullah, et al. ∙

research

∙ 10/23/2020

On Convergence and Generalization of Dropout Training

We study dropout in two-layer neural networks with rectified linear unit...

0 Poorya Mianjy, et al. ∙

research

∙ 10/22/2020

Adversarial Robustness of Supervised Sparse Coding

Several recent results provide theoretical insights into the phenomena o...

0 Jeremias Sulam, et al. ∙

research

∙ 07/15/2020

FetchSGD: Communication-Efficient Federated Learning with Sketching

Existing approaches to federated learning suffer from a communication bo...

0 Daniel Rothchild, et al. ∙

research

∙ 06/17/2020

Is Network the Bottleneck of Distributed Training?

Recently there has been a surge of research on improving the communicati...

0 Zhen Zhang, et al. ∙

research

∙ 06/16/2020

Corralling Stochastic Bandit Algorithms

We study the problem of corralling stochastic bandit algorithms, that is...

0 Raman Arora, et al. ∙

research

∙ 03/06/2020

Dropout: Explicit Forms and Capacity Control

We investigate the capacity control provided by dropout in various machi...

0 Raman Arora, et al. ∙

research

∙ 02/22/2020

Private Stochastic Convex Optimization: Efficient Algorithms for Non-smooth Objectives

In this paper, we revisit the problem of private stochastic convex optim...

0 Raman Arora, et al. ∙

research

∙ 12/30/2019

Multiview Representation Learning for a Union of Subspaces

Canonical correlation analysis (CCA) is a popular technique for learning...

0 Nils Holzenberger, et al. ∙

research

∙ 07/29/2019

Bandits with Feedback Graphs and Switching Costs

We study the adversarial multi-armed bandit problem where partial observ...

4 Raman Arora, et al. ∙

research

∙ 05/28/2019

On Dropout and Nuclear Norm Regularization

We give a formal and complete characterization of the explicit regulariz...

0 Poorya Mianjy, et al. ∙

research

∙ 03/12/2019

Communication-efficient distributed SGD with Sketching

Large-scale distributed training of neural networks is often limited by ...

10 Nikita Ivkin, et al. ∙

research

∙ 11/21/2018

Learning from Multiview Correlations in Open-Domain Videos

An increasing number of datasets contain multiple views, such as video, ...

0 Nils Holzenberger, et al. ∙

research

∙ 11/09/2018

Policy Regret in Repeated Games

The notion of policy regret in online learning is a well defined? perfor...

0 Raman Arora, et al. ∙

research

∙ 08/02/2018

Streaming Kernel PCA with Õ(√(n)) Random Features

We study the statistical and computational aspects of kernel principal c...

0 Enayat Ullah, et al. ∙

research

∙ 06/26/2018

On the Implicit Bias of Dropout

Algorithmic approaches endow deep learning systems with implicit bias th...

0 Poorya Mianjy, et al. ∙

research

∙ 03/30/2018

Visual Robot Task Planning

Prospection, the act of predicting the consequences of many possible fut...

0 Chris Paxton, et al. ∙

research

∙ 11/08/2017

Learning to Imagine Manipulation Goals for Robot Task Planning

Prospection is an important part of how humans come up with new task pla...

0 Chris Paxton, et al. ∙

research

∙ 02/22/2017

Stochastic Approximation for Canonical Correlation Analysis

We study canonical correlation analysis (CCA) as a stochastic optimizati...

0 Raman Arora, et al. ∙

research

∙ 02/08/2017

Deep Generalized Canonical Correlation Analysis

We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a ...

0 Adrian Benton, et al. ∙

research

∙ 12/29/2016

Symmetry, Saddle Points, and Global Geometry of Nonconvex Matrix Factorization

We propose a general theory for studying the geometry of nonconvex objec...

0 Xingguo Li, et al. ∙

research

∙ 11/04/2016

Understanding Deep Neural Networks with Rectified Linear Units

In this paper we investigate the family of functions representable by de...

0 Raman Arora, et al. ∙

research

∙ 07/10/2016

On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization

The cyclic block coordinate descent-type (CBCD-type) methods, which perf...

0 Xingguo Li, et al. ∙

research

∙ 06/29/2016

Disease Trajectory Maps

Medical researchers are coming to appreciate that many diseases are in f...

0 Peter Schulam, et al. ∙

research

∙ 05/25/2016

A First Order Free Lunch for SQRT-Lasso

Many statistical machine learning techniques sacrifice convenient comput...

0 Xingguo Li, et al. ∙

research

∙ 05/09/2016

Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction

We propose a stochastic variance reduced optimization algorithm for solv...

0 Xingguo Li, et al. ∙

research

∙ 04/02/2016

Embedding Lexical Features via Low-Rank Tensors

Modern NLP models rely heavily on engineered features, which often combi...

0 Mo Yu, et al. ∙

research

∙ 07/05/2013

Stochastic Optimization of PCA with Capped MSG

We study PCA as a stochastic optimization problem and propose a novel st...

0 Raman Arora, et al. ∙

research

∙ 06/27/2012

Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret

Online learning algorithms are designed to learn even when their input i...

0 Raman Arora, et al. ∙

Raman Arora

Featured Co-authors