Aryan Mokhtari

Why Does MAML Outperform ERM? An Optimization Perspective

Model-Agnostic Meta-Learning (MAML) has demonstrated widespread success ...
10/27/2020 ∙ by Liam Collins, et al. ∙ 0 ∙ share

read it
Federated Learning with Compression: Unified Analysis and Sharp Guarantees

In federated learning, communication cost is often a critical bottleneck...
07/02/2020 ∙ by Farzin Haddadpour, et al. ∙ 0 ∙ share

read it
Hybrid Model for Anomaly Detection on Call Detail Records by Time Series Forecasting

Mobile network operators store an enormous amount of information like lo...
06/07/2020 ∙ by Aryan Mokhtari, et al. ∙ 23 ∙ share

read it
Non-asymptotic Superlinear Convergence of Standard Quasi-Newton Methods

In this paper, we study the non-asymptotic superlinear convergence rate ...
03/30/2020 ∙ by Qiujiang Jin, et al. ∙ 0 ∙ share

read it
Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs

We consider a decentralized stochastic learning problem where data point...
02/23/2020 ∙ by Hossein Taheri, et al. ∙ 0 ∙ share

read it
Personalized Federated Learning: A Meta-Learning Approach

The goal of federated learning is to design algorithms in which several ...
02/19/2020 ∙ by Alireza Fallah, et al. ∙ 4 ∙ share

read it
Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning

We consider Model-Agnostic Meta-Learning (MAML) methods for Reinforcemen...
02/12/2020 ∙ by Alireza Fallah, et al. ∙ 1 ∙ share

read it
Distribution-Agnostic Model-Agnostic Meta-Learning

The Model-Agnostic Meta-Learning (MAML) algorithm <cit.> has been celebr...
02/12/2020 ∙ by Liam Collins, et al. ∙ 21 ∙ share

read it
A Decentralized Proximal Point-type Method for Saddle Point Problems

In this paper, we focus on solving a class of constrained non-convex non...
10/31/2019 ∙ by Weijie Liu, et al. ∙ 0 ∙ share

read it
One Sample Stochastic Frank-Wolfe

One of the beauties of the projected gradient descent method lies in its...
10/10/2019 ∙ by Mingrui Zhang, et al. ∙ 7 ∙ share

read it
FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization

Federated learning is a new distributed machine learning approach, where...
09/28/2019 ∙ by Amirhossein Reisizadeh, et al. ∙ 18 ∙ share

read it
On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms

In this paper, we study the convergence theory of a class of gradient-ba...
08/27/2019 ∙ by Alireza Fallah, et al. ∙ 0 ∙ share

read it
Robust and Communication-Efficient Collaborative Learning

We consider a decentralized learning problem, where a set of computing n...
07/24/2019 ∙ by Amirhossein Reisizadeh, et al. ∙ 0 ∙ share

read it
Proximal Point Approximations Achieving a Convergence Rate of O(1/k) for Smooth Convex-Concave Saddle Point Problems: Optimistic Gradient and Extra-gradient Methods

In this paper we analyze the iteration complexity of the optimistic grad...
06/03/2019 ∙ by Aryan Mokhtari, et al. ∙ 0 ∙ share

read it
Stochastic Conditional Gradient++

In this paper, we develop Stochastic Continuous Greedy++ (SCG++), the fi...
02/19/2019 ∙ by Hamed Hassani, et al. ∙ 0 ∙ share

read it
Quantized Frank-Wolfe: Communication-Efficient Distributed Optimization

How can we efficiently mitigate the overhead of gradient communications ...
02/17/2019 ∙ by Mingrui Zhang, et al. ∙ 0 ∙ share

read it
A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach

We consider solving convex-concave saddle point problems. We focus on tw...
01/24/2019 ∙ by Aryan Mokhtari, et al. ∙ 0 ∙ share

read it
Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy

In this paper, we propose a Distributed Accumulated Newton Conjugate gra...
10/26/2018 ∙ by Majid Jahani, et al. ∙ 0 ∙ share

read it
Escaping Saddle Points in Constrained Optimization

In this paper, we focus on escaping from saddle points in smooth nonconv...
09/06/2018 ∙ by Aryan Mokhtari, et al. ∙ 0 ∙ share

read it
Quantized Decentralized Consensus Optimization

We consider the problem of decentralized consensus optimization, where t...
06/29/2018 ∙ by Amirhossein Reisizadeh, et al. ∙ 0 ∙ share

read it
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication

Recently, the decentralized optimization problem is attracting growing a...
05/25/2018 ∙ by Zebang Shen, 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
Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization

This paper considers stochastic optimization problems for a large class ...
04/24/2018 ∙ by Aryan Mokhtari, et al. ∙ 0 ∙ share

read it
Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method

We consider large scale empirical risk minimization (ERM) problems, wher...
05/22/2017 ∙ by Mark Eisen, et al. ∙ 0 ∙ share

read it
Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation

Existing approaches to resource allocation for nowadays stochastic netwo...
10/07/2016 ∙ by Tianyi Chen, et al. ∙ 0 ∙ share

read it
A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning

We consider learning problems over training sets in which both, the numb...
06/15/2016 ∙ by Aryan Mokhtari, et al. ∙ 0 ∙ share

read it
RES: Regularized Stochastic BFGS Algorithm

RES, a regularized stochastic version of the Broyden-Fletcher-Goldfarb-S...
01/29/2014 ∙ by Aryan Mokhtari, et al. ∙ 0 ∙ share

read it

Aryan Mokhtari

Featured Co-authors

Xin Wang

Georgios B. Giannakis

Alejandro Ribeiro

Suvrit Sra

Lin Chen

Amin Karbasi

Ali Jadbabaie

Martin Takáč

Peilin Zhao

Sanjay Shakkottai

Hamed Hassani

Why Does MAML Outperform ERM? An Optimization Perspective

Federated Learning with Compression: Unified Analysis and Sharp Guarantees

Hybrid Model for Anomaly Detection on Call Detail Records by Time Series Forecasting

Non-asymptotic Superlinear Convergence of Standard Quasi-Newton Methods

Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs

Personalized Federated Learning: A Meta-Learning Approach

Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning

Distribution-Agnostic Model-Agnostic Meta-Learning

A Decentralized Proximal Point-type Method for Saddle Point Problems

One Sample Stochastic Frank-Wolfe

FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization

On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms

Robust and Communication-Efficient Collaborative Learning

Proximal Point Approximations Achieving a Convergence Rate of O(1/k) for Smooth Convex-Concave Saddle Point Problems: Optimistic Gradient and Extra-gradient Methods

Stochastic Conditional Gradient++

Quantized Frank-Wolfe: Communication-Efficient Distributed Optimization

A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach

Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy

Escaping Saddle Points in Constrained Optimization

Quantized Decentralized Consensus Optimization

Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication

Direct Runge-Kutta Discretization Achieves Acceleration

Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization

Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method

Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation

A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning

RES: Regularized Stochastic BFGS Algorithm