Concept

Théorème de convergence monotone

Publications associées (52)

Learning to Align Sequential Actions in the Wild

Pascal Fua, Bugra Tekin, Weizhe Liu

State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspon- dences across videos in time. They either learn frame-to- frame mapping across sequences, which does not leverage temporal information, or a ...
IEEE2022

On the Double Descent of Random Features Models Trained with SGD

Volkan Cevher, Fanghui Liu

We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/overparameterized regime. In this work, we derive precise non-asymptotic error bounds of RF regression under b ...
2022

Mixed-precision explicit stabilized Runge-Kutta methods for single- and multi-scale differential equations

Giacomo Rosilho De Souza, Matteo Croci

Mixed-precision algorithms combine low-and high-precision computations in order to benefit from the performance gains of reduced-precision without sacrificing accuracy. In this work, we design mixed-precision Runge-Kutta-Chebyshev (RKC) methods, where high ...
ACADEMIC PRESS INC ELSEVIER SCIENCE2022

Decentralized Proximal Gradient Algorithms With Linear Convergence Rates

Ali H. Sayed, Kun Yuan, Sulaiman A S A E Alghunaim

This article studies a class of nonsmooth decentralized multiagent optimization problems where the agents aim at minimizing a sum of local strongly-convex smooth components plus a common nonsmooth term. We propose a general primal-dual algorithmic framewor ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Analytical and Machine Learning Methods for the Complete Safe Coordination of Astrobot Swarms

Matin Macktoobian

The recent generations of massive spectroscopic surveys aim at the ray collection from a multitude of cosmological targets in the course of observations. For this purpose, astrobots are used to change the configuration of optical fibers from one observatio ...
EPFL2021

Variance-Reduced Stochastic Learning Under Random Reshuffling

Ali H. Sayed, Bicheng Ying, Kun Yuan

Several useful variance-reduced stochastic gradient algorithms, such as SVRG, SAGA, Finito, and SAG, have been proposed to minimize empirical risks with linear convergence properties to the exact minimizer. The existing convergence results assume uniform d ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

MATHICSE Technical Report : Generalized Parallel Tempering on Bayesian Inverse Problems

Fabio Nobile, Juan Pablo Madrigal Cianci

In the current work we present two generalizations of the Parallel Tempering algorithm, inspired by the so-called continuous-time Infinite Swapping algorithm. Such a method, found its origins in the molecular dynamics community, and can be understood as th ...
MATHICSE2020

Convergent momentum-space OPE and bootstrap equations in conformal field theory

Marc Gillioz

General principles of quantum field theory imply that there exists an operator product expansion (OPE) for Wightman functions in Minkowski momentum space that converges for arbitrary kinematics. This convergence is guaranteed to hold in the sense of a dist ...
SPRINGER2020

A Bayesian numerical homogenization method for elliptic multiscale inverse problems

Assyr Abdulle, Andrea Di Blasio

A new strategy based on numerical homogenization and Bayesian techniques for solving multiscale inverse problems is introduced. We consider a class of elliptic problems which vary at a microscopic scale, and we aim at recovering the highly oscillatory tens ...
2020

A local discontinuous Galerkin gradient discretization method for linear and quasilinear elliptic equations

Assyr Abdulle, Giacomo Rosilho De Souza

A local weighted discontinuous Galerkin gradient discretization method for solving elliptic equations is introduced. The local scheme is based on a coarse grid and successively improves the solution solving a sequence of local elliptic problems in high gra ...
EDP SCIENCES S A2019

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.