
Exploiting Local Convergence of QuasiNewton Methods Globally: Adaptive Sample Size Approach
In this paper, we study the application of quasiNewton methods for solv...
read it

Generalization of ModelAgnostic MetaLearning Algorithms: Recurring and Unseen Tasks
In this paper, we study the generalization properties of ModelAgnostic ...
read it

Why Does MAML Outperform ERM? An Optimization Perspective
ModelAgnostic MetaLearning (MAML) has demonstrated widespread success ...
read it

Federated Learning with Compression: Unified Analysis and Sharp Guarantees
In federated learning, communication cost is often a critical bottleneck...
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...
read it

Nonasymptotic Superlinear Convergence of Standard QuasiNewton Methods
In this paper, we study the nonasymptotic superlinear convergence rate ...
read it

Quantized Pushsum for Gossip and Decentralized Optimization over Directed Graphs
We consider a decentralized stochastic learning problem where data point...
read it

Personalized Federated Learning: A MetaLearning Approach
The goal of federated learning is to design algorithms in which several ...
read it

Provably Convergent Policy Gradient Methods for ModelAgnostic MetaReinforcement Learning
We consider ModelAgnostic MetaLearning (MAML) methods for Reinforcemen...
read it

DistributionAgnostic ModelAgnostic MetaLearning
The ModelAgnostic MetaLearning (MAML) algorithm <cit.> has been celebr...
read it

A Decentralized Proximal Pointtype Method for Saddle Point Problems
In this paper, we focus on solving a class of constrained nonconvex non...
read it

One Sample Stochastic FrankWolfe
One of the beauties of the projected gradient descent method lies in its...
read it

FedPAQ: A CommunicationEfficient Federated Learning Method with Periodic Averaging and Quantization
Federated learning is a new distributed machine learning approach, where...
read it

On the Convergence Theory of GradientBased ModelAgnostic MetaLearning Algorithms
In this paper, we study the convergence theory of a class of gradientba...
read it

Robust and CommunicationEfficient Collaborative Learning
We consider a decentralized learning problem, where a set of computing n...
read it

Proximal Point Approximations Achieving a Convergence Rate of O(1/k) for Smooth ConvexConcave Saddle Point Problems: Optimistic Gradient and Extragradient Methods
In this paper we analyze the iteration complexity of the optimistic grad...
read it

Stochastic Conditional Gradient++
In this paper, we develop Stochastic Continuous Greedy++ (SCG++), the fi...
read it

Quantized FrankWolfe: CommunicationEfficient Distributed Optimization
How can we efficiently mitigate the overhead of gradient communications ...
read it

A Unified Analysis of Extragradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
We consider solving convexconcave saddle point problems. We focus on tw...
read it

Efficient Distributed Hessian Free Algorithm for Largescale Empirical Risk Minimization via Accumulating Sample Strategy
In this paper, we propose a Distributed Accumulated Newton Conjugate gra...
read it

Escaping Saddle Points in Constrained Optimization
In this paper, we focus on escaping from saddle points in smooth nonconv...
read it

Quantized Decentralized Consensus Optimization
We consider the problem of decentralized consensus optimization, where t...
read it

Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication
Recently, the decentralized optimization problem is attracting growing a...
read it

Direct RungeKutta Discretization Achieves Acceleration
We study gradientbased optimization methods obtained by directly discre...
read it

Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization
This paper considers stochastic optimization problems for a large class ...
read it

Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method
We consider large scale empirical risk minimization (ERM) problems, wher...
read it

Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation
Existing approaches to resource allocation for nowadays stochastic netwo...
read it

A Class of Parallel Doubly Stochastic Algorithms for LargeScale Learning
We consider learning problems over training sets in which both, the numb...
read it

RES: Regularized Stochastic BFGS Algorithm
RES, a regularized stochastic version of the BroydenFletcherGoldfarbS...
read it
Aryan Mokhtari
is this you? claim profile