Results 1  10
of
267
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
, 2010
"... Stochastic subgradient methods are widely used, well analyzed, and constitute effective tools for optimization and online learning. Stochastic gradient methods ’ popularity and appeal are largely due to their simplicity, as they largely follow predetermined procedural schemes. However, most common s ..."
Abstract

Cited by 311 (3 self)
 Add to MetaCart
(Show Context)
Stochastic subgradient methods are widely used, well analyzed, and constitute effective tools for optimization and online learning. Stochastic gradient methods ’ popularity and appeal are largely due to their simplicity, as they largely follow predetermined procedural schemes. However, most common subgradient approaches are oblivious to the characteristics of the data being observed. We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradientbased learning. The adaptation, in essence, allows us to find needles in haystacks in the form of very predictive but rarely seenfeatures. Ourparadigmstemsfromrecentadvancesinstochasticoptimizationandonlinelearning which employ proximal functions to control the gradient steps of the algorithm. We describe and analyze an apparatus for adaptively modifying the proximal function, which significantly simplifies setting a learning rate and results in regret guarantees that are provably as good as the best proximal function that can be chosen in hindsight. In a companion paper, we validate experimentally our theoretical analysis and show that the adaptive subgradient approach outperforms stateoftheart, but nonadaptive, subgradient algorithms. 1
Computational methods for sparse solution of linear inverse problems
, 2009
"... The goal of sparse approximation problems is to represent a target signal approximately as a linear combination of a few elementary signals drawn from a fixed collection. This paper surveys the major practical algorithms for sparse approximation. Specific attention is paid to computational issues, ..."
Abstract

Cited by 167 (0 self)
 Add to MetaCart
The goal of sparse approximation problems is to represent a target signal approximately as a linear combination of a few elementary signals drawn from a fixed collection. This paper surveys the major practical algorithms for sparse approximation. Specific attention is paid to computational issues, to the circumstances in which individual methods tend to perform well, and to the theoretical guarantees available. Many fundamental questions in electrical engineering, statistics, and applied mathematics can be posed as sparse approximation problems, making these algorithms versatile and relevant to a wealth of applications.
Hogwild!: A lockfree approach to parallelizing stochastic gradient descent
, 2011
"... Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve stateoftheart performance on a variety of machine learning tasks. Several researchers have recently proposed schemes to parallelize SGD, but all require performancedestroying memory locking and synchronization. This work a ..."
Abstract

Cited by 161 (9 self)
 Add to MetaCart
(Show Context)
Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve stateoftheart performance on a variety of machine learning tasks. Several researchers have recently proposed schemes to parallelize SGD, but all require performancedestroying memory locking and synchronization. This work aims to show using novel theoretical analysis, algorithms, and implementation that SGD can be implemented without any locking. We present an update scheme called HOGWILD! which allows processors access to shared memory with the possibility of overwriting each other’s work. We show that when the associated optimization problem is sparse, meaning most gradient updates only modify small parts of the decision variable, then HOGWILD! achieves a nearly optimal rate of convergence. We demonstrate experimentally that HOGWILD! outperforms alternative schemes that use locking by an order of magnitude. 1
Dual averaging methods for regularized stochastic learning and online optimization
 In Advances in Neural Information Processing Systems 23
, 2009
"... We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning task, and the other is a simple regularization term such as ℓ1norm for promoting sparsity. We develop extensions of Nes ..."
Abstract

Cited by 133 (7 self)
 Add to MetaCart
(Show Context)
We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning task, and the other is a simple regularization term such as ℓ1norm for promoting sparsity. We develop extensions of Nesterov’s dual averaging method, that can exploit the regularization structure in an online setting. At each iteration of these methods, the learning variables are adjusted by solving a simple minimization problem that involves the running average of all past subgradients of the loss function and the whole regularization term, not just its subgradient. In the case of ℓ1regularization, our method is particularly effective in obtaining sparse solutions. We show that these methods achieve the optimal convergence rates or regret bounds that are standard in the literature on stochastic and online convex optimization. For stochastic learning problems in which the loss functions have Lipschitz continuous gradients, we also present an accelerated version of the dual averaging method.
Parallel stochastic gradient algorithms for largescale matrix completion
 MATHEMATICAL PROGRAMMING COMPUTATION
, 2013
"... This paper develops Jellyfish, an algorithm for solving dataprocessing problems with matrixvalued decision variables regularized to have low rank. Particular examples of problems solvable by Jellyfish include matrix completion problems and leastsquares problems regularized by the nuclear norm or ..."
Abstract

Cited by 74 (8 self)
 Add to MetaCart
This paper develops Jellyfish, an algorithm for solving dataprocessing problems with matrixvalued decision variables regularized to have low rank. Particular examples of problems solvable by Jellyfish include matrix completion problems and leastsquares problems regularized by the nuclear norm or γ2norm. Jellyfish implements a projected incremental gradient method with a biased, random ordering of the increments. This biased ordering allows for a parallel implementation that admits a speedup nearly proportional to the number of processors. On largescale matrix completion tasks, Jellyfish is orders of magnitude more efficient than existing codes. For example, on the Netflix Prize data set, prior art computes rating predictions in approximately 4 hours, while Jellyfish solves the same problem in under 3 minutes on a 12 core workstation.
Optimal distributed online prediction using minibatches
, 2010
"... Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of webscale prediction problems, it is increasingly common to encounter situations where a single processor cannot keep up with the high rate at which inputs arrive. In this wor ..."
Abstract

Cited by 73 (9 self)
 Add to MetaCart
Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of webscale prediction problems, it is increasingly common to encounter situations where a single processor cannot keep up with the high rate at which inputs arrive. In this work, we present the distributed minibatch algorithm, a method of converting many serial gradientbased online prediction algorithms into distributed algorithms. We prove a regret bound for this method that is asymptotically optimal for smooth convex loss functions and stochastic inputs. Moreover, our analysis explicitly takes into account communication latencies between nodes in the distributed environment. We show how our method can be used to solve the closelyrelated distributed stochastic optimization problem, achieving an asymptotically linear speedup over multiple processors. Finally, we demonstrate the merits of our approach on a webscale online prediction problem.
A stochastic gradient method with an exponential convergence rate for finite training sets.
 In NIPS,
, 2012
"... Abstract We propose a new stochastic gradient method for optimizing the sum of a finite set of smooth functions, where the sum is strongly convex. While standard stochastic gradient methods converge at sublinear rates for this problem, the proposed method incorporates a memory of previous gradient ..."
Abstract

Cited by 73 (10 self)
 Add to MetaCart
Abstract We propose a new stochastic gradient method for optimizing the sum of a finite set of smooth functions, where the sum is strongly convex. While standard stochastic gradient methods converge at sublinear rates for this problem, the proposed method incorporates a memory of previous gradient values in order to achieve a linear convergence rate. Numerical experiments indicate that the new algorithm can dramatically outperform standard algorithms.
An optimal method for stochastic composite optimization
 Mathematical Programming Series A
, 2010
"... This paper considers an important class of convex programming problems whose objective function Ψ is given by the summation of a smooth and nonsmooth component. Further, it is assumed that the only information available for the numerical scheme to solve these problems is the subgradient of Ψ contam ..."
Abstract

Cited by 67 (12 self)
 Add to MetaCart
(Show Context)
This paper considers an important class of convex programming problems whose objective function Ψ is given by the summation of a smooth and nonsmooth component. Further, it is assumed that the only information available for the numerical scheme to solve these problems is the subgradient of Ψ contaminated by stochastic noise. Our contribution mainly consists of the following aspects. Firstly, with a novel analysis, it is demonstrated that the simple robust mirrordescent stochastic approximation method applied to the aforementioned problems exhibits the best known so far rate of convergence guaranteed by a more involved stochastic mirrorprox algorithm. Moreover, by incorporating some ideas of the optimal method for smooth minimization, we propose an accelerated scheme, which can achieve, uniformly in dimension, the theoretically optimal rate of convergence for solving this class of problems. Finally, the significant advantages of the accelerated scheme over the existing algorithms are illustrated in the context of solving a class of stochastic programming problems whose feasible region is a simple compact convex set intersected with an affine manifold.
Distributed delayed stochastic optimization
, 2011
"... We analyze the convergence of gradientbased optimization algorithms whose updates depend on delayed stochastic gradient information. The main application of our results is to the development of distributed minimizationalgorithmswhereamasternodeperformsparameterupdateswhile worker nodes compute stoc ..."
Abstract

Cited by 55 (6 self)
 Add to MetaCart
We analyze the convergence of gradientbased optimization algorithms whose updates depend on delayed stochastic gradient information. The main application of our results is to the development of distributed minimizationalgorithmswhereamasternodeperformsparameterupdateswhile worker nodes compute stochastic gradients based on local information in parallel, which may give rise to delays due to asynchrony. Our main contributionistoshowthatforsmoothstochasticproblems,thedelaysareasymptotically negligible. In application to distributed optimization, we show nnode architectures whose optimization error in stochastic problems—in spite of asynchronous delays—scales asymptotically as O(1 / √ nT), which is known to be optimal even in the absence of delays. 1
Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization, I: a generic algorithmic framework.
, 2010
"... Abstract In this paper we study new stochastic approximation (SA) type algorithms, namely, the accelerated SA (ACSA), for solving strongly convex stochastic composite optimization (SCO) problems. Specifically, by introducing a domain shrinking procedure, we significantly improve the largedeviatio ..."
Abstract

Cited by 48 (9 self)
 Add to MetaCart
(Show Context)
Abstract In this paper we study new stochastic approximation (SA) type algorithms, namely, the accelerated SA (ACSA), for solving strongly convex stochastic composite optimization (SCO) problems. Specifically, by introducing a domain shrinking procedure, we significantly improve the largedeviation results associated with the convergence rate of a nearly optimal ACSA algorithm presented in