paper-with-me

Papers

ASAGA: Asynchronous Parallel SAGA

2016-06-15 · Rémi Leblond, Fabian Pedregosa, Simon Lacoste-Julien

We describe ASAGA, an asynchronous parallel version of the incremental gradient algorithm SAGA that enjoys fast linear convergence rates. Through a novel perspective, we revisit and clarify a subtle but important technical issue present in a large fraction of the recent convergence rate proofs for asynchronous parallel optimization algorithms, and propose a simplification of the recently introduced "perturbed iterate" framework that resolves it. We thereby prove that ASAGA can obtain a theoretical linear speedup on multi-core systems even without sparsity assumptions. We present results of an implementation on a 40-core architecture illustrating the practical speedup as well as the hardware overhead.

📄 PDF Abstract BibTeX arXiv:1606.04809

Code (1)

RemiLeblond/ASAGA 공식 구현

Methods 이 논문이 사용한 방법론

SAGA SAGA is a method in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the…

Similar Papers 제목 키워드 기반

Improved asynchronous parallel optimization analysis for stochastic incremental methods

2018-01-11 · Rémi Leblond, Fabian Pedregosa, Simon Lacoste-Julien

As datasets continue to increase in size and multi-core computer architectures are developed, asynchronous parallel optimization algorithms become more and more essential to the field of Machine Learning. Unfortunately, …

Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization

2017-07-20 · NeurIPS 2017 12 · Fabian Pedregosa, Rémi Leblond, Simon Lacoste-Julien

Due to their simplicity and excellent performance, parallel asynchronous variants of stochastic gradient descent have become popular methods to solve a wide range of large-scale optimization problems on multi-core archit…

Accelerated Variance Reduced Stochastic Extragradient Method for Sparse Machine Learning Problems

2019-09-25 · Fanhua Shang, Lin Kong, Yuanyuan Liu, Hua Huang 외

Recently, many stochastic gradient descent algorithms with variance reduction have been proposed. Moreover, their proximal variants such as Prox-SVRG can effectively solve non-smooth problems, which makes that they are w…

BIG-bench Machine LearningFace RecognitionRobust Face Recognition

Asynchronous Distributed Optimization with Stochastic Delays

2020-09-22 · Margalit Glasgow, Mary Wootters

We study asynchronous finite sum minimization in a distributed-data setting with a central parameter server. While asynchrony is well understood in parallel settings where the data is accessible by all machines -- e.g., …

Distributed Optimization

aSAGA: Automatic Sleep Analysis with Gray Areas

2023-10-03 · Matias Rusanen, Gabriel Jouan, Riku Huttunen, Sami Nikkonen 외

State-of-the-art automatic sleep staging methods have already demonstrated comparable reliability and superior time efficiency to manual sleep staging. However, fully automatic black-box solutions are difficult to adapt …

Explainable artificial intelligenceSleep Staging