Concept

Multiplication operator

Publications associées (6)

Stochastic distributed learning with gradient quantization and double-variance reduction

Sebastian Urban Stich, Konstantin Mishchenko

We consider distributed optimization over several devices, each sending incremental model updates to a central server. This setting is considered, for instance, in federated learning. Various schemes have been designed to compress the model updates in orde ...

TAYLOR & FRANCIS LTD2022

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Martin Jaggi, Sebastian Urban Stich, Quentin Rebjock, Sai Praneeth Reddy Karimireddy

Sign-based algorithms (e.g. signSGD) have been proposed as a biased gradient compression technique to alleviate the communication bottleneck in training large neural networks across multiple workers. We show simple convex counter-examples where signSGD doe ...

PMLR2019

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Martin Jaggi, Sebastian Urban Stich, Quentin Rebjock, Sai Praneeth Reddy Karimireddy

2019

Local Well-Posedness And Blow-Up For The Half Ginzburg-Landau-Kuramoto Equation With Rough Coefficients And Potential

Luigi Forcella

We study the Cauchy problem for the half Ginzburg- Landau-Kuramoto (hGLK) equation with the second order elliptic operator having rough coecients and potential type perturbation. The blow-up of solutions for hGLK equation with non-positive nonlinearity is ...

2019

Compact Q-Learning Optimized for Micro-robots with Processing and Memory Constraints

Roland Siegwart, Masoud Asadpour

Scaling down robots to miniature size introduces many new challenges including memory and program size limitations, low processor performance and low power autonomy. In this paper we describe the concept and implementation of learning of a safewandering ta ...

2004

Compact Q-Learning for Micro-robots

Roland Siegwart, Masoud Asadpour

2003

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.

Connectez-vous pour utiliser Chat avec Graph Search