Search Results for author: Louis Leconte

Found 6 papers, 0 papers with code

Boolean Logic as an Error feedback mechanism

no code implementations29 Jan 2024 Louis Leconte

The notion of Boolean logic backpropagation was introduced to build neural networks with weights and activations being Boolean numbers.

FAVANO: Federated AVeraging with Asynchronous NOdes

no code implementations25 May 2023 Louis Leconte, Van Minh Nguyen, Eric Moulines

In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource-constrained environments.

Federated Learning

AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks

no code implementations7 Nov 2022 Louis Leconte, Sholom Schechtman, Eric Moulines

First, we formulate the training of quantized neural networks (QNNs) as a smoothed sequence of interval-constrained optimization problems.

Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning

no code implementations11 Jun 2021 Eugene Belilovsky, Louis Leconte, Lucas Caccia, Michael Eickenberg, Edouard Oyallon

With the use of a replay buffer we show that this approach can be extended to asynchronous settings, where modules can operate and continue to update with possibly large communication delays.

Image Classification Quantization

Interferometric Graph Transform for Community Labeling

no code implementations4 Jun 2021 Nathan Grinsztajn, Louis Leconte, Philippe Preux, Edouard Oyallon

We present a new approach for learning unsupervised node representations in community graphs.

Cannot find the paper you are looking for? You can Submit a new open access paper.