2021
Proximal Gradient Methods with Adaptive Subspace Sampling
Many applications in machine learning or signal processing involve nonsmooth optimization problems. This nonsmoothness brings a …
2020
Sparse Asynchronous Distributed Learning
In this talk, we present an asynchronous distributed learning algorithm where parameter updates are performed by worker machines …
2019
Identification-Based First-Order Algorithms for Distributed Learning
In this talk, we present a first-order optimization algorithm for distributed learning problems. We propose an efficient sparsification …
Distributed First-Order Optimization with Tamed Communications
Many machine learning and signal processing applications involve high-dimensional nonsmooth optimization problems. The nonsmoothness is …
Identify and Sparsify$:$ Distributed Optimization with Asynchronous Moderate Communications
We present an asynchronous optimization algorithm for distributed learning, that efficiently reduces the communications between a …
Identify and Sparsify$:$ Distributed Optimization with Asynchronous Moderate Communications
We present an asynchronous optimization algorithm for distributed learning, that efficiently reduces the communications between a …
2018
Distributed Optimization with Sparse Communications and Structure Identification
We propose an efficient distributed algorithm for solving regularized learning problems. In a distributed framework with a master …
Distributed Optimization with Sparse Communications and Structure Identification
We propose an efficient distributed algorithm for solving regularized learning problems. In a distributed framework with a master …
Distributed Optimization with Sparse Communications
We present an asynchronous optimization algorithm for distributed learning, that efficiently reduces the communications between a …
2016
Solving of Minimal Mutual Information Model Problem via Regularization of Dual Problem and Using Ellipsoid Method with Inexact Oracle
In this work, we study the problem of restoring the correspondence matrix for measuring the flows on the links of a large computer …