Publications related to Accelerated ADMM based on Accelerated Douglas-Rachford Splitting

On the Generalization of Stochastic Gradient Descent with Momentum

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Brookline2024

Orientation-dependent two-dimensional magnonic crystal modes in an ultralow-damping ferrimagnetic waveguide containing repositioned hexagonal lattices of Cu disks

Dirk Grundler

Two-dimensional (2D) hexagonal lattices of Cu disks are shown to induce orientation-dependent magnonic crystal (MC) modes for propagating forward volume spin waves in a single-crystal yttrium iron garnet (YIG) film. The width and depth of the magnonic band ...

2024

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Pore size estimation in axon-mimicking microfibers with diffusion-relaxation MRI

Jean-Philippe Thiran, Erick Jorge Canales Rodriguez, Muhamed Barakovic, Marco Pizzolato, Tim Bjørn Dyrby

Purpose: This study aims to evaluate two distinct approaches for fiber radius estimation using diffusion-relaxation MRI data acquired in biomimetic microfiber phantoms that mimic hollow axons. The methods considered are the spherical mean power-law approac ...

Hoboken2024

Iterative removal of sources to model the turbulent electromotive force

Abhijit Bhausaheb Bendre

We describe a novel method to compute the components of dynamo tensors from direct magnetohydrodynamic (MHD) simulations. Our method relies upon an extension and generalization of the standard H & ouml;gbom CLEAN algorithm widely used in radio astronomy to ...

Oxford Univ Press2024

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Anastasiia Koloskova

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

EPFL2024

Improving SAM Requires Rethinking its Optimization Formulation

Volkan Cevher, Kimon Antonakopoulos, Thomas Michaelsen Pethick, Wanyun Xie, Fabian Ricardo Latorre Gomez

This paper rethinks Sharpness-Aware Minimization (SAM), which is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. We argue that SAM shou ...

2024

A Combination Technique for Optimal Control Problems Constrained by Random PDEs

Fabio Nobile, Tommaso Vanzan

We present a combination technique based on mixed differences of both spatial approximations and quadrature formulae for the stochastic variables to solve efficiently a class of optimal control problems (OCPs) constrained by random partial differential equ ...

2024

On the fast assemblage of finite element matrices with application to nonlinear heat transfer problems

The finite element method is a well-established method for the numerical solution of partial differential equations (PDEs), both linear and nonlinear. However, the repeated re -assemblage of finite element matrices for nonlinear PDEs is frequently pointed ...

ELSEVIER SCIENCE INC2023

Testing Benchmark for a Block Conjugate Gradient Solving Scheme in Poroelasticity

With the advancement in fields of science more complex and more coupled phenomena can be explained, calculated and predicted. To solve these problems one has to update the related tools. Since analytical solutions do not exist for all physical processes, s ...

2023

Accelerated ADMM based on Accelerated Douglas-Rachford Splitting

Graph Chatbot

Chat with Graph Search

On the Generalization of Stochastic Gradient Descent with Momentum

Orientation-dependent two-dimensional magnonic crystal modes in an ultralow-damping ferrimagnetic waveguide containing repositioned hexagonal lattices of Cu disks

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Pore size estimation in axon-mimicking microfibers with diffusion-relaxation MRI

Iterative removal of sources to model the turbulent electromotive force

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Improving SAM Requires Rethinking its Optimization Formulation

A Combination Technique for Optimal Control Problems Constrained by Random PDEs

On the fast assemblage of finite element matrices with application to nonlinear heat transfer problems

Testing Benchmark for a Block Conjugate Gradient Solving Scheme in Poroelasticity

On the Generalization of Stochastic Gradient Descent with Momentum

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Orientation-dependent two-dimensional magnonic crystal modes in an ultralow-damping ferrimagnetic waveguide containing repositioned hexagonal lattices of Cu disks

Pore size estimation in axon-mimicking microfibers with diffusion-relaxation MRI

Iterative removal of sources to model the turbulent electromotive force

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

A Combination Technique for Optimal Control Problems Constrained by Random PDEs

On the fast assemblage of finite element matrices with application to nonlinear heat transfer problems

Testing Benchmark for a Block Conjugate Gradient Solving Scheme in Poroelasticity

Improving SAM Requires Rethinking its Optimization Formulation