Distributed optimization with arbitrary local solvers
With the growth of data and necessity for distributed optimization methods, solvers that work
well on a single machine must be re-designed to leverage distributed computation. Recent …
well on a single machine must be re-designed to leverage distributed computation. Recent …
From server-based to client-based machine learning: A comprehensive survey
In recent years, mobile devices have gained increasing development with stronger
computation capability and larger storage space. Some of the computation-intensive …
computation capability and larger storage space. Some of the computation-intensive …
Stochastic, distributed and federated optimization for machine learning
J Konečný - arXiv preprint arXiv:1707.01155, 2017 - arxiv.org
We study optimization algorithms for the finite sum problems frequently arising in machine
learning applications. First, we propose novel variants of stochastic gradient descent with a …
learning applications. First, we propose novel variants of stochastic gradient descent with a …
Efficient distributed hessian free algorithm for large-scale empirical risk minimization via accumulating sample strategy
In this paper, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE)
method in which sample size is gradually increasing to quickly obtain a solution whose …
method in which sample size is gradually increasing to quickly obtain a solution whose …
Preconditioned conjugate gradient methods in truncated newton frameworks for large-scale linear classification
Truncated Newton method is one of the most effective optimization methods for large-scale
linear classification. The main computational task at each Newton iteration is to …
linear classification. The main computational task at each Newton iteration is to …
A class of parallel doubly stochastic algorithms for large-scale learning
We consider learning problems over training sets in which both, the number of training
examples and the dimension of the feature vectors, are large. To solve these problems we …
examples and the dimension of the feature vectors, are large. To solve these problems we …
Communication lower bounds for distributed convex optimization: Partition data on features
Recently, there has been an increasing interest in designing distributed convex optimization
algorithms under the setting where the data matrix is partitioned on features. Algorithms …
algorithms under the setting where the data matrix is partitioned on features. Algorithms …
[PDF][PDF] Grow Your Samples and Optimize Better via Distributed Newton CG and Accumulating Strategy
In this work1, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE)
method in which sample size is gradually increasing to quickly obtain a solution whose …
method in which sample size is gradually increasing to quickly obtain a solution whose …
[PDF][PDF] Distributed Algorithms in Large-scaled Empirical Risk Minimization: Non-convexity, Adaptive Sampling, and Matrix-free Second-order Methods
X He - 2019 - core.ac.uk
Abstract 1 1 Dual Free Adaptive Mini-batch SDCA for Empirical Risk Minimization 3 1.1
Introduction..................................... 3 1.1. 1 Contributions................................ 5 1.1. 2 …
Introduction..................................... 3 1.1. 1 Contributions................................ 5 1.1. 2 …
Distributed Restarting NewtonCG Method for Large-Scale Empirical Risk Minimization
In this paper, we propose a distributed damped Newton method in which sample size is
gradually increasing to quickly obtain a solution whose empirical loss is under satisfactory …
gradually increasing to quickly obtain a solution whose empirical loss is under satisfactory …