Naman Agarwal

is this you? claim profile

0 followers
Google ∙ Princeton University

Online Control with Adversarial Disturbances

We study the control of a linear dynamical system with adversarial distu...
02/23/2019 ∙ by Naman Agarwal, et al. ∙ 8 ∙ share

read it
Disentangling Adaptive Gradient Methods from Learning Rates

We investigate several confounding factors in the evaluation of optimiza...
02/26/2020 ∙ by Naman Agarwal, et al. ∙ 6 ∙ share

read it
Leverage Score Sampling for Faster Accelerated Regression and ERM

Given a matrix A∈R^n× d and a vector b ∈R^d, we show how to compute an ϵ...
11/22/2017 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Lower Bounds for Higher-Order Convex Optimization

State-of-the-art methods in convex and non-convex optimization employ hi...
10/27/2017 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
The Price of Differential Privacy For Online Learning

We design differentially private algorithms for the problem of online li...
01/27/2017 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Finding Approximate Local Minima Faster than Gradient Descent

We design a non-convex second-order optimization algorithm that is guara...
11/03/2016 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Second-Order Stochastic Optimization for Machine Learning in Linear Time

First-order stochastic methods are the state-of-the-art in large-scale m...
02/12/2016 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Multisection in the Stochastic Block Model using Semidefinite Programming

We consider the problem of identifying underlying community-like structu...
07/08/2015 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Effective Dimension of Exp-concave Optimization

We investigate the role of the effective (a.k.a. statistical) dimension ...
05/21/2018 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
The Case for Full-Matrix Adaptive Regularization

Adaptive regularization methods come in diagonal and full-matrix variant...
06/08/2018 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
cpSGD: Communication-efficient and differentially-private distributed SGD

Distributed stochastic gradient descent is an important subroutine in di...
05/27/2018 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Extreme Tensoring for Low-Memory Preconditioning

State-of-the-art models are now trained with billions of parameters, rea...
02/12/2019 ∙ by Xinyi Chen, et al. ∙ 0 ∙ share

read it
Design and Development of Underwater Vehicle: ANAHITA

Anahita is an autonomous underwater vehicle which is currently being dev...
03/01/2019 ∙ by Akash Jain, et al. ∙ 0 ∙ share

read it
Boosting for Dynamical Systems

We propose a framework of boosting for learning and control in environme...
06/20/2019 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Logarithmic Regret for Online Control

We study optimal regret bounds for control in linear dynamical systems u...
09/11/2019 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
A Deep Conditioning Treatment of Neural Networks

We study the role of depth in training randomly initialized overparamete...
02/04/2020 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it

Naman Agarwal

Featured Co-authors

Yi Zhang

Sham M. Kakade

Sanjiv Kumar

Aaron Sidford

Tengyu Ma

Elad Hazan

Zeyuan Allen-Zhu

Praneeth Netrapalli

Yin Tat Lee

Sham Kakade

Ananda Theertha Suresh

Online Control with Adversarial Disturbances

Disentangling Adaptive Gradient Methods from Learning Rates

Leverage Score Sampling for Faster Accelerated Regression and ERM

Lower Bounds for Higher-Order Convex Optimization

The Price of Differential Privacy For Online Learning

Finding Approximate Local Minima Faster than Gradient Descent

Second-Order Stochastic Optimization for Machine Learning in Linear Time

Multisection in the Stochastic Block Model using Semidefinite Programming

Effective Dimension of Exp-concave Optimization

The Case for Full-Matrix Adaptive Regularization

cpSGD: Communication-efficient and differentially-private distributed SGD

Extreme Tensoring for Low-Memory Preconditioning

Design and Development of Underwater Vehicle: ANAHITA

Boosting for Dynamical Systems

Logarithmic Regret for Online Control

A Deep Conditioning Treatment of Neural Networks