Results 1  10
of
176,669
Projectionfree Online Learning
"... The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projections in favor of much more efficient linear optimization steps using the FrankWolfe technique. We obtain a range of regret ..."
Abstract

Cited by 26 (5 self)
 Add to MetaCart
The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projections in favor of much more efficient linear optimization steps using the FrankWolfe technique. We obtain a range
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
Search and replication in unstructured peertopeer networks
, 2002
"... Abstract Decentralized and unstructured peertopeer networks such as Gnutella are attractive for certain applicationsbecause they require no centralized directories and no precise control over network topologies and data placement. However, the floodingbased query algorithm used in Gnutella does n ..."
Abstract

Cited by 692 (6 self)
 Add to MetaCart
propose a query algorithm based on multiple random walks that resolves queries almost as quickly as gnutella's flooding method while reducing the network traffic by two orders of magnitude in many cases. We also present a distributed replication strategy that yields closetooptimal performance
Efficient sparse coding algorithms
 In NIPS
, 2007
"... Sparse coding provides a class of algorithms for finding succinct representations of stimuli; given only unlabeled input data, it discovers basis functions that capture higherlevel features in the data. However, finding sparse codes remains a very difficult computational problem. In this paper, we ..."
Abstract

Cited by 445 (14 self)
 Add to MetaCart
present efficient sparse coding algorithms that are based on iteratively solving two convex optimization problems: an L1regularized least squares problem and an L2constrained least squares problem. We propose novel algorithms to solve both of these optimization problems. Our algorithms result in a
Multiple kernel learning, conic duality, and the SMO algorithm
 In Proceedings of the 21st International Conference on Machine Learning (ICML
, 2004
"... While classical kernelbased classifiers are based on a single kernel, in practice it is often desirable to base classifiers on combinations of multiple kernels. Lanckriet et al. (2004) considered conic combinations of kernel matrices for the support vector machine (SVM), and showed that the optimiz ..."
Abstract

Cited by 445 (31 self)
 Add to MetaCart
that the optimization of the coefficients of such a combination reduces to a convex optimization problem known as a quadraticallyconstrained quadratic program (QCQP). Unfortunately, current convex optimization toolboxes can solve this problem only for a small number of kernels and a small number of data points
The Complexity of Decentralized Control of Markov Decision Processes
 Mathematics of Operations Research
, 2000
"... We consider decentralized control of Markov decision processes and give complexity bounds on the worstcase running time for algorithms that find optimal solutions. Generalizations of both the fullyobservable case and the partiallyobservable case that allow for decentralized control are described. ..."
Abstract

Cited by 411 (46 self)
 Add to MetaCart
We consider decentralized control of Markov decision processes and give complexity bounds on the worstcase running time for algorithms that find optimal solutions. Generalizations of both the fullyobservable case and the partiallyobservable case that allow for decentralized control are described
A firstorder primaldual algorithm for convex problems with applications to imaging
, 2010
"... In this paper we study a firstorder primaldual algorithm for convex optimization problems with known saddlepoint structure. We prove convergence to a saddlepoint with rate O(1/N) in finite dimensions, which is optimal for the complete class of nonsmooth problems we are considering in this paper ..."
Abstract

Cited by 436 (20 self)
 Add to MetaCart
In this paper we study a firstorder primaldual algorithm for convex optimization problems with known saddlepoint structure. We prove convergence to a saddlepoint with rate O(1/N) in finite dimensions, which is optimal for the complete class of nonsmooth problems we are considering
Revisiting frankwolfe: Projectionfree sparse convex optimization
 In ICML
, 2013
"... We provide stronger and more general primaldual convergence results for FrankWolfetype algorithms (a.k.a. conditional gradient) for constrained convex optimization, enabled by a simple framework of duality gap certificates. Our analysis also holds if the linear subproblems are only solved approxi ..."
Abstract

Cited by 86 (2 self)
 Add to MetaCart
We provide stronger and more general primaldual convergence results for FrankWolfetype algorithms (a.k.a. conditional gradient) for constrained convex optimization, enabled by a simple framework of duality gap certificates. Our analysis also holds if the linear subproblems are only solved
VarianceReduced and ProjectionFree Stochastic Optimization
"... Abstract The FrankWolfe optimization algorithm has recently regained popularity for machine learning applications due to its projectionfree property and its ability to handle structured constraints. However, in the stochastic learning setting, it is still relatively understudied compared to the g ..."
Abstract
 Add to MetaCart
Abstract The FrankWolfe optimization algorithm has recently regained popularity for machine learning applications due to its projectionfree property and its ability to handle structured constraints. However, in the stochastic learning setting, it is still relatively understudied compared
Sparse Reconstruction by Separable Approximation
, 2007
"... Finding sparse approximate solutions to large underdetermined linear systems of equations is a common problem in signal/image processing and statistics. Basis pursuit, the least absolute shrinkage and selection operator (LASSO), waveletbased deconvolution and reconstruction, and compressed sensing ..."
Abstract

Cited by 373 (38 self)
 Add to MetaCart
of minimizing the sum of a smooth convex function and a nonsmooth, possibly nonconvex, sparsityinducing function. We propose iterative methods in which each step is an optimization subproblem involving a separable quadratic term (diagonal Hessian) plus the original sparsityinducing term. Our approach
Results 1  10
of
176,669