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.
The interest for distributed stochastic optimization has raised to train complex Machine Learning models with more data on distributed systems. Increasing the computation power speeds up the training but it faces a communication bottleneck between workers ...
In modern-data analysis applications, the abundance of data makes extracting meaningful information from it challenging, in terms of computation, storage, and interpretability. In this setting, exploiting sparsity in data has been essential to the developm ...
In this study, we developed a robust inversion algorithm to estimate the Neurite Orientation Dispersion and Density Imaging (NODDI) model. It is based on the Accelerated Microstructure Imaging via Convex Optimization (AMICO) framework. However, in contrast ...
We present new results concerning the approximation of the total variation, ∫Ω∣∇u∣, of a function u by non-local, non-convex functionals of the form $$ \Lambda_\delta u = \int_{\Omega} \int_{\Omega} \frac{\delta \varphi \big( |u(x) - ...
Decentralized optimization is a powerful paradigm that finds applications in engineering and learning design. This work studies decentralized composite optimization problems with non-smooth regularization terms. Most existing gradient-based proximal decent ...
Recently, Kannan et al. [2018] proposed several logit regularization methods to improve the adversarial robustness of classifiers. We show that the computationally fast methods they propose - Clean Logit Pairing (CLP) and Logit Squeezing (LSQ) - just make ...
Mini-batch stochastic gradient descent (SGD) is state of the art in large scale distributed training. The scheme can reach a linear speedup with respect to the number of workers, but this is rarely seen in practice as the scheme often suffers from large ne ...
The analysis in Part I [1] revealed interesting properties for subgradient learning algorithms in the context of stochastic optimization. These algorithms are used when the risk functions are non-smooth or involve non-differentiable components. They have b ...
Recent advances in statistical learning and convex optimization have inspired many successful practices. Standard theories assume smoothness---bounded gradient, Hessian, etc.---and strong convexity of the loss function. Unfortunately, such conditions may ...
Background: One of the tasks in the 2017 iDASH secure genome analysis competition was to enable training of logistic regression models over encrypted genomic data. More precisely, given a list of approximately 1500 patient records, each with 18 binary feat ...
