Publication

CoCoA: A General Framework for Communication-Efficient Distributed Optimization

Résumé

The scale of modern datasets necessitates the development of efficient distributed optimization methods for machine learning. We present a general-purpose framework for distributed computing environments, CoCoA, that has an efficient communication scheme and is applicable to a wide variety of problems in machine learning and signal processing. We extend the framework to cover general non-strongly-convex regularizers, including L1-regularized problems like lasso, sparse logistic regression, and elastic net regularization, and show how earlier work can be derived as a special case. We provide convergence guarantees for the class of convex regularized loss minimization objectives, leveraging a novel approach in handling non-strongly-convex regularizers and non-smooth loss functions. The resulting framework has markedly improved performance over state-of-the-art methods, as we illustrate with an extensive set of experiments on real distributed datasets.

À propos de ce résultat
Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.
Concepts associés (32)
Elastic net regularization
In statistics and, in particular, in the fitting of linear or logistic regression models, the elastic net is a regularized regression method that linearly combines the L1 and L2 penalties of the lasso and ridge methods. The elastic net method overcomes the limitations of the LASSO (least absolute shrinkage and selection operator) method which uses a penalty function based on Use of this penalty function has several limitations. For example, in the "large p, small n" case (high-dimensional data with few examples), the LASSO selects at most n variables before it saturates.
Régularisation (mathématiques)
vignette|Les courbes bleues et vertes correspondent à deux modèles differents, tous les deux étant des solutions possibles du problème consistant à décrire les coordonnées de tous les points rouges. L'application d'une régularisation favorise le modèle moins complexe correspondant à la courbe verte. Dans le domaine des mathématiques et des statistiques, et plus particulièrement dans le domaine de l'apprentissage automatique, la régularisation fait référence à un processus consistant à ajouter de l'information à un problème, s'il est mal posé ou pour éviter le surapprentissage.
Lasso (statistiques)
En statistiques, le lasso est une méthode de contraction des coefficients de la régression développée par Robert Tibshirani dans un article publié en 1996 intitulé Regression shrinkage and selection via the lasso. Le nom est un acronyme anglais : Least Absolute Shrinkage and Selection Operator. Bien que cette méthode fut utilisée à l'origine pour des modèles utilisant l'estimateur usuel des moindres carrés, la pénalisation lasso s'étend facilement à de nombreux modèles statistiques tels que les modèles linéaires généralisés, les modèles à risque proportionnel, et les M-estimateurs.
Afficher plus
Publications associées (62)

Efficient local linearity regularization to overcome catastrophic overfitting

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...
2024

Machine learning models for prediction of electrochemical properties in supercapacitor electrodes using MXene and graphene nanoplatelets

Mohammad Khaja Nazeeruddin

Herein, machine learning (ML) models using multiple linear regression (MLR), support vector regression (SVR), random forest (RF) and artificial neural network (ANN) are developed and compared to predict the output features viz. specific capacitance (Csp), ...
Lausanne2024

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Volkan Cevher, Fanghui Liu

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...
2024
Afficher plus
MOOCs associés (10)
Digital Signal Processing [retired]
The course provides a comprehensive overview of digital signal processing theory, covering discrete time, Fourier analysis, filter design, sampling, interpolation and quantization; it also includes a
Digital Signal Processing
Digital Signal Processing is the branch of engineering that, in the space of just a few decades, has enabled unprecedented levels of interpersonal communication and of on-demand entertainment. By rewo
Afficher plus