Publications associées (12)

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Rachid Guerraoui, Nirupam Gupta, Youssef Allouah, Geovani Rizk, Rafaël Benjamin Pinot

The theory underlying robust distributed learning algorithms, designed to resist adversarial machines, matches empirical observations when data is homogeneous. Under data heterogeneity however, which is the norm in practical scenarios, established lower bo ...
2023

Self-Exciting Point Processes: Identification and Control

Michael Mark

This thesis addresses theoretical and practical aspects of identification and subsequent control of self-exciting point processes. The main contributions correspond to four separate scientific papers.In the first paper, we address the challenge of robust i ...
EPFL2022

The KDD 2021 Workshop on Causal Discovery (CD2021)

Negar Kiyavash, Huan Liu

As a basic and effective tool for explanation, prediction and decision making, causal relationships have been utilized in almost all disciplines. Traditionally, causal relationships are identified by making use of interventions or randomized controlled exp ...
ASSOC COMPUTING MACHINERY2021

Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning

Ali H. Sayed, Jie Chen, Stefan Vlaski, Roula Nassif

The problem of simultaneously learning several related tasks has received considerable attention in several domains, especially in machine learning, with the so-called multitask learning (MTL) problem, or learning to learn problem [1], [2]. MTL is an appro ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

An Alternate Statistical Lens to Look at Collaboration Data: Extreme Value Theory

Kshitij Sharma, Jennifer Kaitlyn Olsen

To provide beneficial feedback to students during their collaboration, it is important to identify behaviors that are indicative of good collaboration. However, in a collaborative learning session, students engage in a range of behaviors and it can be diff ...
2019

From structure to application: studies on adenine-, pyrene- and lanthanide-based metal-organic frameworks

Andrzej Gladysiak

Metal-organic frameworks (MOFs) are coordination polymer materials in which inorganic metal ions or clusters are linked with multitopic organic ligands by means of coordination bonds. Their structural versatility allows for design of materials based on pre ...
EPFL2019

Studying Teacher Cognitive Load in Multi-tabletop Classrooms Using Mobile Eye-tracking

Pierre Dillenbourg, Kshitij Sharma, Luis Pablo Prieto Santos, Daniela Caballero Díaz, Yun Wen

Increasing affordability is making multi-tabletop spaces (e.g., in school classrooms) a real possibility, and first design guidelines for such environments are starting to appear. However, there are still very few studies into the usability of such multi-t ...
ACM2014

About similar characteristics of visual perceptual learning and LTP

Michael Herzog, Carl Kristoffer Aberg

Perceptual learning is an implicit form of learning which induces long-lasting perceptual enhancements. Perceptual learning shows intriguing characteristics. For example, a minimal number of trials per session is needed for learning and the interleaved pre ...
2012

Classifying Material in the Real World

Barbara Caputo

Classifying materials from their appearance is challenging. Impressive results have been obtained under varying illumination and pose conditions. Still, the effect of scale variations and the possibility to generalise across different material samples are ...
2009

Classifying Materials in the Real World

Barbara Caputo

Classifying materials from their appearance is challenging. Impressive results have been obtained under varying illumination and pose conditions. Still, the effect of scale variations and the possibility to generalize across different material samples are ...
IDIAP2007

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.