Results 1  10
of
1,019
Fast linear iterations for distributed averaging.
 Systems & Control Letters,
, 2004
"... Abstract We consider the problem of finding a linear iteration that yields distributed averaging consensus over a network, i.e., that asymptotically computes the average of some initial values given at the nodes. When the iteration is assumed symmetric, the problem of finding the fastest converging ..."
Abstract

Cited by 433 (12 self)
 Add to MetaCart
be exploited to speed up interiorpoint methods for solving the fastest distributed linear iteration problem, for networks with up to a thousand or so edges. We also describe a simple subgradient method that handles far larger problems, with up to one hundred thousand edges. We give several extensions
Lambertian Reflectance and Linear Subspaces
, 2000
"... We prove that the set of all reflectance functions (the mapping from surface normals to intensities) produced by Lambertian objects under distant, isotropic lighting lies close to a 9D linear subspace. This implies that, in general, the set of images of a convex Lambertian object obtained under a wi ..."
Abstract

Cited by 526 (20 self)
 Add to MetaCart
the effects of Lambertian materials as the analog of a convolution. These results allow us to construct algorithms for object recognition based on linear methods as well as algorithms that use convex optimization to enforce nonnegative lighting functions. Finally, we show a simple way to enforce non
Pegasos: Primal Estimated subgradient solver for SVM
"... We describe and analyze a simple and effective stochastic subgradient descent algorithm for solving the optimization problem cast by Support Vector Machines (SVM). We prove that the number of iterations required to obtain a solution of accuracy ɛ is Õ(1/ɛ), where each iteration operates on a singl ..."
Abstract

Cited by 542 (20 self)
 Add to MetaCart
We describe and analyze a simple and effective stochastic subgradient descent algorithm for solving the optimization problem cast by Support Vector Machines (SVM). We prove that the number of iterations required to obtain a solution of accuracy ɛ is Õ(1/ɛ), where each iteration operates on a
A Singular Value Thresholding Algorithm for Matrix Completion
, 2008
"... This paper introduces a novel algorithm to approximate the matrix with minimum nuclear norm among all matrices obeying a set of convex constraints. This problem may be understood as the convex relaxation of a rank minimization problem, and arises in many important applications as in the task of reco ..."
Abstract

Cited by 555 (22 self)
 Add to MetaCart
of recovering a large matrix from a small subset of its entries (the famous Netflix problem). Offtheshelf algorithms such as interior point methods are not directly amenable to large problems of this kind with over a million unknown entries. This paper develops a simple firstorder and easy
Training Support Vector Machines: an Application to Face Detection
, 1997
"... We investigate the application of Support Vector Machines (SVMs) in computer vision. SVM is a learning technique developed by V. Vapnik and his team (AT&T Bell Labs.) that can be seen as a new method for training polynomial, neural network, or Radial Basis Functions classifiers. The decision sur ..."
Abstract

Cited by 727 (1 self)
 Add to MetaCart
global optimality, and can be used to train SVM's over very large data sets. The main idea behind the decomposition is the iterative solution of subproblems and the evaluation of optimality conditions which are used both to generate improved iterative values, and also establish the stopping
Cones of matrices and setfunctions and 01 optimization
 SIAM JOURNAL ON OPTIMIZATION
, 1991
"... It has been recognized recently that to represent a polyhedron as the projection of a higher dimensional, but simpler, polyhedron, is a powerful tool in polyhedral combinatorics. We develop a general method to construct higherdimensional polyhedra (or, in some cases, convex sets) whose projection a ..."
Abstract

Cited by 347 (7 self)
 Add to MetaCart
approximates the convex hull of 01 valued solutions of a system of linear inequalities. An important feature of these approximations is that one can optimize any linear objective function over them in polynomial time. In the special case of the vertex packing polytope, we obtain a sequence of systems
A Growing Neural Gas Network Learns Topologies
 Advances in Neural Information Processing Systems 7
, 1995
"... An incremental network model is introduced which is able to learn the important topological relations in a given set of input vectors by means of a simple Hebblike learning rule. In contrast to previous approaches like the "neural gas" method of Martinetz and Schulten (1991, 1994), this m ..."
Abstract

Cited by 401 (5 self)
 Add to MetaCart
An incremental network model is introduced which is able to learn the important topological relations in a given set of input vectors by means of a simple Hebblike learning rule. In contrast to previous approaches like the "neural gas" method of Martinetz and Schulten (1991, 1994
Probing the Pareto frontier for basis pursuit solutions
, 2008
"... The basis pursuit problem seeks a minimum onenorm solution of an underdetermined leastsquares problem. Basis pursuit denoise (BPDN) fits the leastsquares problem only approximately, and a single parameter determines a curve that traces the optimal tradeoff between the leastsquares fit and the ..."
Abstract

Cited by 365 (5 self)
 Add to MetaCart
and the onenorm of the solution. We prove that this curve is convex and continuously differentiable over all points of interest, and show that it gives an explicit relationship to two other optimization problems closely related to BPDN. We describe a rootfinding algorithm for finding arbitrary points
Convex multitask feature learning
 MACHINE LEARNING
, 2007
"... We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the wellknown singletask 1norm regularization. It is based on a novel nonconvex regularizer which controls the number of learned features common across the tasks. We prove th ..."
Abstract

Cited by 258 (25 self)
 Add to MetaCart
that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task
PROJECTED NEWTON METHODS FOR OPTIMIZATION PROBLEMS WITH SIMPLE CONSTRAINTS
, 1982
"... We consider the problem min {f(x)\x 201, and propose algorithms of the form xk+, = [xtakDkvf(xk)]+, where [.I+ denotes projection on the positive orthant, ak is a stepsize chosen by an Armijolike rule and Dk is a positive definite symmetric matrix which is partly diagonal. We show that Dk can be ..."
Abstract

Cited by 143 (4 self)
 Add to MetaCart
be calculated simply on the basis of second derivatives off so that the resulting Newtonlike algorithm has a typically superlinear rate of convergence. With other choices of Dk convergence at a typically linear rate is obtained. The algorithms are almost as simple as their unconstrained counterparts
Results 1  10
of
1,019