Publications associées à Méthode du gradient conjugué

SPEEDING UP KRYLOV SUBSPACE METHODS FOR COMPUTING f(A)b VIA RANDOMIZATION

This work is concerned with the computation of the action of a matrix function f(A), such as the matrix exponential or the matrix square root, on a vector b. For a general matrix A, this can be done by computing the compression of A onto a suitable Krylov ...

Siam Publications2024

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

Randomized flexible GMRES with deflated restarting

Laura Grigori, Emeric Martin

For a high-dimensional problem, a randomized Gram-Schmidt (RGS) algorithm is beneficial in terms of both computational cost and numerical stability. We apply this dimension reduction technique by random sketching to Krylov subspace methods, e.g., to the ge ...

Springer2024

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

Fast Adversarial Training With Adaptive Step Size

Mathieu Salzmann, Sabine Süsstrunk, Chen Liu, Zhuoyi Huang, Yong Zhang, Jue Wang

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to ...

Ieee-Inst Electrical Electronics Engineers Inc2023

Efficient and Accurate Handling of Periodic Flows in Time-Sensitive Networks

Jean-Yves Le Boudec, Seyed Mohammadhossein Tabatabaee

Total Flow Analysis (TFA) is a method for the worst-case analysis of time-sensitive networks. It uses service curve characterizations of the network nodes and arrival curves of flows at their sources; for tractability, the latter are often taken to be line ...

2023

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Volkan Cevher, Thomas Michaelsen Pethick, Wanyun Xie

This paper presents a theoretical analysis of linear interpolation as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss lan ...

2023

An optimal preconditioned FFT-accelerated finite element solver for homogenization

Till Junge, Ali Falsafi, Martin Ladecký

We generalize and provide a linear algebra-based perspective on a finite element (FE) ho-mogenization scheme, pioneered by Schneider et al. (2017)[1] and Leuschner and Fritzen (2018)[2]. The efficiency of the scheme is based on a preconditioned, well-scale ...

ELSEVIER SCIENCE INC2023

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti, Liang Xu

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretiz ...

2023

Implicit Distance Functions: Learning and Applications in Robotics

Mikhail Koptev

In this thesis, we address the complex issue of collision avoidance in the joint space of robots. Avoiding collisions with both the robot's own body parts and obstacles in the environment is a critical constraint in motion planning and is crucial for ensur ...

EPFL2023