Publications associées à Walkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization

A Least-Squares/Relaxation Method for the Numerical Solution of the Three-Dimensional Elliptic Monge-Ampere Equation

Alexandre Caboussat, Dimitrios Gourzoulidis

In this article, we address the numerical solution of the Dirichlet problem for the three-dimensional elliptic Monge-Ampere equation using a least-squares/relaxation approach. The relaxation algorithm allows the decoupling of the differential operators fro ...

SPRINGER/PLENUM PUBLISHERS2018

Efficient Variance-Reduced Learning Over Multi-Agent Networks

Ali H. Sayed, Bicheng Ying, Kun Yuan

This work develops a fully decentralized variance-reduced learning algorithm for multi-agent networks where nodes store and process the data locally and are only allowed to communicate with their immediate neighbors. In the proposed algorithm, there is no ...

IEEE COMPUTER SOC2018

A coordinator-driven communication reduction scheme for distributed optimization using the projected gradient method

Colin Neil Jones, Georgios Stathopoulos

We propose a way to estimate the value function of a convex proximal minimization problem. The scheme constructs a convex set within which the optimizer resides and iteratively refines the set every time that the value function is sampled, namely every tim ...

2018

A coordinator-driven communication reduction scheme for distributed optimization using the projected gradient method

Colin Neil Jones, Georgios Stathopoulos

We propose a way to estimate the value function of a convex proximal minimization problem. The scheme constructs a convex set within which the optimizer resides and iteratively refines the set every time that the value function is sampled, namely every tim ...

IEEE2018

Non-local Functionals Related to the Total Variation and Connections with Image Processing

Hoài-Minh Nguyên

We present new results concerning the approximation of the total variation,

\int_{\Omega} |\nabla u|

, of a function

u

by non-local, non-convex functionals of the form $$ \Lambda_\delta u = \int_{\Omega} \int_{\Omega} \frac{\delta \varphi \big( |u(x) - ...

2018

Exact Diffusion for Distributed Optimization and Learning---Part II: Convergence Analysis

Ali H. Sayed, Bicheng Ying, Kun Yuan

Part I of this work developed the exact diffusion algorithm to remove the bias that is characteristic of distributed solutions for deterministic optimization problems. The algorithm was shown to be applicable to a larger set of combination policies than ea ...

2017

On Coordinated Primal-Dual Interior-Point Methods for Multi-Agent Optimization

Colin Neil Jones, Altug Bitlislioglu

This paper presents a coordinated primal-dual interior point (PDIP) method for solving structured convex linear and quadratic programs (LP-QP) in a distributed man- ner. The considered class of problems represents a multi-agent setting, where the aggregate ...

2017

Asynchronous updates for stochastic gradient descent

Alberto Silvio Chiappa

Finding convergence rates for numerical optimization algorithms is an important task, because it gives a justification to their use in solving practical problems, while also providing a way to compare their efficiency. This is especially useful in an async ...

2017

Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization

Ulugbek Kamilov

Generalized linear models, where a random vector x is observed through a noisy, possibly nonlinear, function of a linear transform z = A x, arise in a range of applications in nonlinear filtering and regression. Approximate message passing (AMP) methods, b ...

IEEE2017

Fréchet means in Wasserstein space

Yoav Zemel

This work studies the problem of statistical inference for Fréchet means in the Wasserstein space of measures on Euclidean spaces,

\mathcal W_2 ( \mathbb R^d )

. This question arises naturally from the problem of separating amplitude and phase variation i ...

EPFL2017

Walkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization

Graph Chatbot

Chattez avec Graph Search

A Least-Squares/Relaxation Method for the Numerical Solution of the Three-Dimensional Elliptic Monge-Ampere Equation

Efficient Variance-Reduced Learning Over Multi-Agent Networks

A coordinator-driven communication reduction scheme for distributed optimization using the projected gradient method

A coordinator-driven communication reduction scheme for distributed optimization using the projected gradient method

Non-local Functionals Related to the Total Variation and Connections with Image Processing

Exact Diffusion for Distributed Optimization and Learning---Part II: Convergence Analysis

On Coordinated Primal-Dual Interior-Point Methods for Multi-Agent Optimization

Asynchronous updates for stochastic gradient descent

Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization

Fréchet means in Wasserstein space

A Least-Squares/Relaxation Method for the Numerical Solution of the Three-Dimensional Elliptic Monge-Ampere Equation

Fréchet means in Wasserstein space

Asynchronous updates for stochastic gradient descent

A coordinator-driven communication reduction scheme for distributed optimization using the projected gradient method

Efficient Variance-Reduced Learning Over Multi-Agent Networks

A coordinator-driven communication reduction scheme for distributed optimization using the projected gradient method

Non-local Functionals Related to the Total Variation and Connections with Image Processing

Exact Diffusion for Distributed Optimization and Learning---Part II: Convergence Analysis

Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization

On Coordinated Primal-Dual Interior-Point Methods for Multi-Agent Optimization