Publications associées à Connexionnisme

Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search

Rachid Guerraoui, Andrei Kucharavy, Matteo Monti

Modern machine learning (ML) models are capable of impressive performances. However, their prowess is not due only to the improvements in their architecture and training algorithms but also to a drastic increase in computational power used to train them.|S ...

New York2023

Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning

Alexandre Massoud Alahi, Yuejiang Liu

Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In t ...

2023

Get More for Less in Decentralized Learning Systems

Anne-Marie Kermarrec, Rafael Pereira Pires, Akash Balasaheb Dhasade, Rishi Sharma, Milos Vujasinovic, Jeffrey Wigger

Decentralized learning (DL) systems have been gaining popularity because they avoid raw data sharing by communicating only model parameters, hence preserving data confidentiality. However, the large size of deep neural networks poses a significant challeng ...

2023

Kernel Memory Networks: A Unifying Framework for Memory Modeling

Wulfram Gerstner, Johanni Michael Brea, Georgios Iatropoulos

We consider the problem of training a neural network to store a set of patterns with maximal noise robustness. A solution, in terms of optimal weights and state update rules, is derived by training each individual neuron to perform either kernel classifica ...

2022

Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation

Robert West, Eda Bayram, Alberto Garcia Duran

The existing literature on knowledge graph completion mostly focuses on the link prediction task. However, knowledge graphs have an additional incompleteness problem: their nodes possess numerical attributes, whose values are often missing. Our approach, d ...

2020

Hardware Implementation of Neural Self-Interference Cancellation

Andreas Peter Burg, Alexios Konstantinos Balatsoukas Stimming, Andreas Toftegaard Kristensen, Yann Kurzo

In-band full-duplex systems can transmit and receive information simultaneously and on the same frequency band. However, due to the strong self-interference caused by the transmitter to its own receiver, the use of non-linear digital self-interference canc ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

Volkan Cevher, Paul Thierry Yves Rolland, Fabian Ricardo Latorre Gomez

We introduce LiPopt, a polynomial optimization framework for computing increasingly tighter upper bounds on the Lipschitz constant of neural networks. The underlying optimization problems boil down to either linear (LP) or semidefinite (SDP) programming. W ...

2020

Overcoming Multi-model Forgetting

Mathieu Salzmann, Anthony Christopher Davison, Martin Jaggi, Yassine Benyahia, Claudiu-Cristian Musat, Kaicheng Yu

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, ...

JMLR2019

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.

Connexionnisme

Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search

Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

Get More for Less in Decentralized Learning Systems

Kernel Memory Networks: A Unifying Framework for Memory Modeling

Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation

Model Fusion via Optimal Transport

Hardware Implementation of Neural Self-Interference Cancellation

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

Overcoming Multi-model Forgetting

Graph Chatbot

Chattez avec Graph Search

Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation

Get More for Less in Decentralized Learning Systems

Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search

Kernel Memory Networks: A Unifying Framework for Memory Modeling

Hardware Implementation of Neural Self-Interference Cancellation

Model Fusion via Optimal Transport

Overcoming Multi-model Forgetting

Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization