Search Results for author: Nikolaos M. Freris

Found 5 papers, 0 papers with code

FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity

no code implementations7 Apr 2022 Yonghai Gong, Yichuan Li, Nikolaos M. Freris

Federated Learning (FL) is an emerging framework for distributed processing of large data volumes by edge devices subject to limited communication bandwidths, heterogeneity in data distributions and computational resources, as well as privacy considerations.

Federated Learning

A Novel Sequential Coreset Method for Gradient Descent Algorithms

no code implementations5 Dec 2021 Jiawei Huang, Ruomin Huang, Wenjie Liu, Nikolaos M. Freris, Hu Ding

A wide range of optimization problems arising in machine learning can be solved by gradient descent algorithms, and a central question in this area is how to efficiently compress a large-scale dataset so as to reduce the computational complexity.

Data Compression

Sparse Travel Time Estimation from Streaming Data

no code implementations22 Apr 2018 Saif Eddin Jabari, Nikolaos M. Freris, Deepthi Mary Dilip

The second shortcoming is the wide-spread use of Gaussian probability densities as mixture components.

Travel Time Estimation

SUCAG: Stochastic Unbiased Curvature-aided Gradient Method for Distributed Optimization

no code implementations22 Mar 2018 Hoi-To Wai, Nikolaos M. Freris, Angelia Nedic, Anna Scaglione

We propose and analyze a new stochastic gradient method, which we call Stochastic Unbiased Curvature-aided Gradient (SUCAG), for finite sum optimization problems.

Distributed Optimization

Recursive Compressed Sensing

no code implementations17 Dec 2013 Nikolaos M. Freris, Orhan Öçal, Martin Vetterli

We introduce a recursive algorithm for performing compressed sensing on streaming data.

Cannot find the paper you are looking for? You can Submit a new open access paper.