Cahiers du GERAD
Recherche
Liste chronologique
3159 résultats — page 20 de 158
One of the major challenges in large-scale distributed machine learning involving stochastic gradient methods is the high cost of gradient communication ove...
référence BibTeXNeural network sparsification using Gibbs measures
Pruning methods for deep neural networks based on weight magnitude have shown promise in recent research. We propose a new, highly flexible approach to neura...
référence BibTeXDeep learning for proactive cooperative malware detection system
The past few years have seen the ability of cooperative Malware Detection Systems (MDS) to detect complex and unknown malware. In a cooperative setting, an M...
référence BibTeXState of compact architecture search for deep neural networks
The design of compact deep neural networks is a crucial task to enable widespread adoption of deep neural networks in the real-world, particularly for edge a...
référence BibTeXUncertainty transfer with knowledge distillation
Knowledge distillation is a technique that consists in training a student network, usually of a low capacity, to mimic the representation space and the perfo...
référence BibTeXSemi+-supervised learning under sample selection bias
In time-to-event data analysis, the main object of interest is the time elapsed between the occurrence of two ordered events, say E1,E2
. Sampling fr...
Training large-scale deep neural networks is a long, time-consuming operation, often requiring many GPUs to accelerate. In large models, the time spent loadi...
référence BibTeXRandom bias initialization improves quantized training
Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful...
référence BibTeXConvergence of gradient methods on bilinear zero-sum games
Min-max formulations have attracted great attention in the ML community due to the rise of deep generative models and adversarial methods, while understandin...
référence BibTeXStatistical learning with the determinantal point process
The determinantal point process (DPP) provides a promising and attractive alternative to simple random sampling in cluster analysis or classification, for th...
référence BibTeXDeep LDA-pruned nets and their robustness
Deep neural networks usually have unnecessarily high complexities and possibly many features of low utility, especially for tasks that they are not designed ...
référence BibTeXShallow Structured Potts Neural Network Regression (S-SPNNR)
We introduce a novel ensemble learning approach which combines random partitions models through Potts clustering with a non-parametric predictor such as sha...
référence BibTeX
Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large ...
référence BibTeXBatch normalization in quantized networks
Implementation of quantized neural networks on computing hardware leads to considerable speed up and memory saving. However, quantized deep networks are diff...
référence BibTeX
In the area of hydraulic power generation, there is a great deal of interest in two interdependent domains: operation and maintenance. This interdependence...
référence BibTeXThe Covering-Assignment Problem for swarm-powered ad-hoc clouds: A distributed 3D mapping use-case
The popularity of drones is rapidly increasing across the different sectors of the economy. Aerial capabilities and relatively low costs make drones the perf...
référence BibTeX
The context of this research is multiobjective optimization where conflicting objectives are present. In this work, these objectives are only available as th...
référence BibTeXA Simulation model for short and long term humanitarian supply chain operations management
Traditionally, the design of supply chains for humanitarian operations has been developed distinctly for the different disaster management phases, with littl...
référence BibTeXOn the interplay between self-driving cars and public transportation: A game-theoretic perspective
Cities worldwide struggle with overloaded transportation systems and their externalities, such as traffic congestion and emissions. The emerging technology o...
référence BibTeXOn the impact of the power production function approximation on hydropower maintenance scheduling
Maintenance planning for hydropower plants is a crucial problem. In this paper, we evaluate the impact of the Hydropower Production Function (HPF) formulatio...
référence BibTeX