Results 1  10
of
77
Guaranteed minimumrank solutions of linear matrix equations via nuclear norm minimization
, 2007
"... The affine rank minimization problem consists of finding a matrix of minimum rank that satisfies a given system of linear equality constraints. Such problems have appeared in the literature of a diverse set of fields including system identification and control, Euclidean embedding, and collaborative ..."
Abstract

Cited by 218 (15 self)
 Add to MetaCart
The affine rank minimization problem consists of finding a matrix of minimum rank that satisfies a given system of linear equality constraints. Such problems have appeared in the literature of a diverse set of fields including system identification and control, Euclidean embedding, and collaborative filtering. Although specific instances can often be solved with specialized algorithms, the general affine rank minimization problem is NPhard, because it contains vector cardinality minimization as a special case. In this paper, we show that if a certain restricted isometry property holds for the linear transformation defining the constraints, the minimum rank solution can be recovered by solving a convex optimization problem, namely the minimization of the nuclear norm over the given affine space. We present several random ensembles of equations where the restricted isometry property holds with overwhelming probability, provided the codimension of the subspace is sufficiently large. The techniques used in our analysis have strong parallels in the compressed sensing framework. We discuss how affine rank minimization generalizes this preexisting concept and outline a dictionary relating concepts from cardinality minimization to those of rank minimization. We also discuss several algorithmic approaches to solving the norm minimization relaxations, and illustrate our results with numerical examples.
Primaldual subgradient methods for convex problems
, 2005
"... (after revision) In this paper we present a new approach for constructing subgradient schemes for different types of nonsmooth problems with convex structure. Our methods are primaldual since they are always able to generate a feasible approximation to the optimum of an appropriately formulated dual ..."
Abstract

Cited by 75 (1 self)
 Add to MetaCart
(after revision) In this paper we present a new approach for constructing subgradient schemes for different types of nonsmooth problems with convex structure. Our methods are primaldual since they are always able to generate a feasible approximation to the optimum of an appropriately formulated dual problem. Besides other advantages, this useful feature provides the methods with a reliable stopping criterion. The proposed schemes differ from the classical approaches (divergent series methods, mirror descent methods) by presence of two control sequences. The first sequence is responsible for aggregating the support functions in the dual space, and the second one establishes a dynamically updated scale between the primal and dual spaces. This additional flexibility allows to guarantee a boundedness of the sequence of primal test points even in the case of unbounded feasible set. We present the variants of subgradient schemes for nonsmooth convex minimization, minimax problems, saddle point problems, variational inequalities, and stochastic optimization. In all situations our methods are proved to be optimal from the view point of worstcase blackbox lower complexity bounds.
Proxmethod with rate of convergence o(1/t) for variational inequalities with lipschitz continuous monotone operators and smooth convexconcave saddlepoint problems
 SIAM Journal on Optimization
"... Abstract. We propose a proxtype method with efficiency estimate O(ɛ−1) for approximating saddle points of convexconcave C1,1 functions and solutions of variational inequalities with monotone Lipschitz continuous operators. Application examples include matrix games, eigenvalue minimization, and com ..."
Abstract

Cited by 73 (12 self)
 Add to MetaCart
Abstract. We propose a proxtype method with efficiency estimate O(ɛ−1) for approximating saddle points of convexconcave C1,1 functions and solutions of variational inequalities with monotone Lipschitz continuous operators. Application examples include matrix games, eigenvalue minimization, and computing the Lovasz capacity number of a graph, and these are illustrated by numerical experiments with largescale matrix games and Lovasz capacity problems.
Efficient Projections onto the ℓ1Ball for Learning in High Dimensions
"... We describe efficient algorithms for projecting a vector onto the ℓ1ball. We present two methods for projection. The first performs exact projection in O(n) expected time, where n is the dimension of the space. The second works on vectors k of whose elements are perturbed outside the ℓ1ball, proje ..."
Abstract

Cited by 67 (9 self)
 Add to MetaCart
We describe efficient algorithms for projecting a vector onto the ℓ1ball. We present two methods for projection. The first performs exact projection in O(n) expected time, where n is the dimension of the space. The second works on vectors k of whose elements are perturbed outside the ℓ1ball, projecting in O(k log(n)) time. This setting is especially useful for online learning in sparse feature spaces such as text categorization applications. We demonstrate the merits and effectiveness of our algorithms in numerous batch and online learning tasks. We show that variants of stochastic gradient projection methods augmented with our efficient projection procedures outperform interior point methods, which are considered stateoftheart optimization techniques. We also show that in online settings gradient updates with ℓ1 projections outperform the exponentiated gradient algorithm while obtaining models with high degrees of sparsity. 1.
Exponentiated gradient algorithms for conditional random fields and maxmargin Markov networks
, 2008
"... Loglinear and maximummargin models are two commonlyused methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore an important problem, and becomes a key factor when learning from very large dat ..."
Abstract

Cited by 59 (1 self)
 Add to MetaCart
Loglinear and maximummargin models are two commonlyused methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore an important problem, and becomes a key factor when learning from very large data sets. This paper describes exponentiated gradient (EG) algorithms for training such models, where EG updates are applied to the convex dual of either the loglinear or maxmargin objective function; the dual in both the loglinear and maxmargin cases corresponds to minimizing a convex function with simplex constraints. We study both batch and online variants of the algorithm, and provide rates of convergence for both cases. In the maxmargin case, O ( 1 ε) EG updates are required to reach a given accuracy ε in the dual; in contrast, for loglinear models only O(log (1/ε)) updates are required. For both the maxmargin and loglinear cases, our bounds suggest that the online EG algorithm requires a factor of n less computation to reach a desired accuracy than the batch EG algorithm, where n is the number of training examples. Our experiments confirm that the online algorithms are much faster than the batch algorithms in practice. We describe how the EG updates factor in a convenient way for structured prediction problems, allowing the algorithms to be
Efficient Online and Batch Learning using Forward Backward Splitting
"... We describe, analyze, and experiment with a framework for empirical loss minimization with regularization. Our algorithmic framework alternates between two phases. On each iteration we first perform an unconstrained gradient descent step. We then cast and solve an instantaneous optimization problem ..."
Abstract

Cited by 56 (1 self)
 Add to MetaCart
We describe, analyze, and experiment with a framework for empirical loss minimization with regularization. Our algorithmic framework alternates between two phases. On each iteration we first perform an unconstrained gradient descent step. We then cast and solve an instantaneous optimization problem that trades off minimization of a regularization term while keeping close proximity to the result of the first phase. This view yields a simple yet effective algorithm that can be used for batch penalized risk minimization and online learning. Furthermore, the two phase approach enables sparse solutions when used in conjunction with regularization functions that promote sparsity, such as ℓ1. We derive concrete and very simple algorithms for minimization of loss functions with ℓ1, ℓ2, ℓ 2 2, and ℓ ∞ regularization. We also show how to construct efficient algorithms for mixednorm ℓ1/ℓq regularization. We further extend the algorithms and give efficient implementations for very highdimensional data with sparsity. We demonstrate the potential of the proposed framework in a series of experiments with synthetic and natural datasets.
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 42 (0 self)
 Add to MetaCart
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
Exponentiated gradient algorithms for loglinear structured prediction
 In Proc. ICML
, 2007
"... Conditional loglinear models are a commonly used method for structured prediction. Efficient learning of parameters in these models is therefore an important problem. This paper describes an exponentiated gradient (EG) algorithm for training such models. EG is applied to the convex dual of the maxi ..."
Abstract

Cited by 29 (5 self)
 Add to MetaCart
Conditional loglinear models are a commonly used method for structured prediction. Efficient learning of parameters in these models is therefore an important problem. This paper describes an exponentiated gradient (EG) algorithm for training such models. EG is applied to the convex dual of the maximum likelihood objective; this results in both sequential and parallel update algorithms, where in the sequential algorithm parameters are updated in an online fashion. We provide a convergence proof for both algorithms. Our analysis also simplifies previous results on EG for maxmargin models, and leads to a tighter bound on convergence rates. Experiments on a largescale parsing task show that the proposed algorithm converges much faster than conjugategradient and LBFGS approaches both in terms of optimization objective and test error. 1.
Informationtheoretic lower bounds on the oracle complexity of convex optimization
 in Proc. Adv. Neural Inf. Process. Syst
"... Abstract—Relative to the large literature on upper bounds on complexity of convex optimization, lesser attention has been paid to the fundamental hardness of these problems. Given the extensive use of convex optimization in machine learning and statistics, gaining an understanding of these complexit ..."
Abstract

Cited by 29 (7 self)
 Add to MetaCart
Abstract—Relative to the large literature on upper bounds on complexity of convex optimization, lesser attention has been paid to the fundamental hardness of these problems. Given the extensive use of convex optimization in machine learning and statistics, gaining an understanding of these complexitytheoretic issues is important. In this paper, we study the complexity of stochastic convex optimization in an oracle model of computation. We introduce a new notion of discrepancy between functions, and use it to reduce problems of stochastic convex optimization to statistical parameter estimation, which can be lower bounded using informationtheoretic methods. Using this approach, we improve upon known results and obtain tight minimax complexity estimates for various function classes. Index Terms—Computational learning theory, convex optimization, Fano’s inequality, informationbased complexity, minimax analysis, oracle complexity. I.
Composite Objective Mirror Descent
"... We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstorder algorithms, such as the projected gradient method, mirror descent, and forwardbackward splitting, our method yields n ..."
Abstract

Cited by 27 (5 self)
 Add to MetaCart
We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstorder algorithms, such as the projected gradient method, mirror descent, and forwardbackward splitting, our method yields new analysis and algorithms. We also derive specific instantiations of our method for commonly used regularization functions, such as ℓ1, mixed norm, and tracenorm. 1