Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Leconte, Louis"'
Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes inference, training is consider
Externí odkaz:
http://arxiv.org/abs/2405.16339
We introduce ReALLM, a novel approach for compression and memory-efficient adaptation of pre-trained language models that encompasses most of the post-training quantization and fine-tuning methods for a budget of <4 bits. Pre-trained matrices are dec
Externí odkaz:
http://arxiv.org/abs/2405.13155
We study asynchronous federated learning mechanisms with nodes having potentially different computational speeds. In such an environment, each node is allowed to work on models with potential delays and contribute to updates to the central server at
Externí odkaz:
http://arxiv.org/abs/2405.00017
Autor:
Leconte, Louis
The notion of Boolean logic backpropagation was introduced to build neural networks with weights and activations being Boolean numbers. Most of computations can be done with Boolean logic instead of real arithmetic, both during training and inference
Externí odkaz:
http://arxiv.org/abs/2401.16418
In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity, ``classical'' federated learning faces the in
Externí odkaz:
http://arxiv.org/abs/2305.16099
In this paper, we develop a new algorithm, Annealed Skewed SGD - AskewSGD - for training deep neural networks (DNNs) with quantized weights. First, we formulate the training of quantized neural networks (QNNs) as a smoothed sequence of interval-const
Externí odkaz:
http://arxiv.org/abs/2211.03741
A commonly cited inefficiency of neural network training using back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full network before updating. Several alternatives that can alleviate this iss
Externí odkaz:
http://arxiv.org/abs/2106.06401
We present a new approach for learning unsupervised node representations in community graphs. We significantly extend the Interferometric Graph Transform (IGT) to community labeling: this non-linear operator iteratively extracts features that take ad
Externí odkaz:
http://arxiv.org/abs/2106.05875
In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVAS, for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity, ``classical'' federated learning faces the inc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::628a0a2b95e5ab5405de66f91e684ede
Autor:
Leconte, Louis-Maurice.
Th.--Méd.--Paris, 1927.
Paris, 1927, n ° 496.
Paris, 1927, n ° 496.
Externí odkaz:
http://catalogue.bnf.fr/ark:/12148/cb369017525