Results 1  10
of
53,768
Algorithms for Nonnegative Matrix Factorization
 In NIPS
, 2001
"... Nonnegative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. Two different multiplicative algorithms for NMF are analyzed. They differ only slightly in the multiplicative factor used in the update rules. One algorithm can be shown to minim ..."
Abstract

Cited by 1230 (5 self)
 Add to MetaCart
Nonnegative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. Two different multiplicative algorithms for NMF are analyzed. They differ only slightly in the multiplicative factor used in the update rules. One algorithm can be shown to minimize the conventional least squares error while the other minimizes the generalized KullbackLeibler divergence. The monotonic convergence of both algorithms can be proven using an auxiliary function analogous to that used for proving convergence of the ExpectationMaximization algorithm. The algorithms can also be interpreted as diagonally rescaled gradient descent, where the rescaling factor is optimally chosen to ensure convergence.
Probabilistic Latent Semantic Analysis
 In Proc. of Uncertainty in Artificial Intelligence, UAI’99
, 1999
"... Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of twomode and cooccurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas. Compared to standard Latent Sema ..."
Abstract

Cited by 760 (9 self)
 Add to MetaCart
Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of twomode and cooccurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas. Compared to standard Latent Semantic Analysis which stems from linear algebra and performs a Singular Value Decomposition of cooccurrence tables, the proposed method is based on a mixture decomposition derived from a latent class model. This results in a more principled approach which has a solid foundation in statistics. In order to avoid overfitting, we propose a widely applicable generalization of maximum likelihood model fitting by tempered EM. Our approach yields substantial and consistent improvements over Latent Semantic Analysis in a number of experiments.
Trade Policy and Economic Growth: A Skeptic's Guide to the CrossNational Evidence
 Macroeconomics Annual 2000, Ben Bemanke and
, 2000
"... Andrew Warner for generously sharing their data with us. We are particularly grateful to BenDavid, Frankel, Romer, Sachs, Warner and Romain Wacziarg for helpful email exchanges. We have benefited greatly from discussions in seminars at the University of California at Berkeley, ..."
Abstract

Cited by 1013 (25 self)
 Add to MetaCart
Andrew Warner for generously sharing their data with us. We are particularly grateful to BenDavid, Frankel, Romer, Sachs, Warner and Romain Wacziarg for helpful email exchanges. We have benefited greatly from discussions in seminars at the University of California at Berkeley,
The Cyclical Behavior of Equilibrium Unemployment and Vacancies
 American Economic Review
, 2005
"... This paper argues that a broad class of search models cannot generate the observed businesscyclefrequency fluctuations in unemployment and job vacancies in response to shocks of a plausible magnitude. In the U.S., the vacancyunemployment ratio is 20 times as volatile as average labor productivity ..."
Abstract

Cited by 839 (20 self)
 Add to MetaCart
This paper argues that a broad class of search models cannot generate the observed businesscyclefrequency fluctuations in unemployment and job vacancies in response to shocks of a plausible magnitude. In the U.S., the vacancyunemployment ratio is 20 times as volatile as average labor productivity, while under weak assumptions, search models predict that the vacancyunemployment ratio and labor productivity have nearly the same variance. I establish this claim both using analytical comparative statics in a very general deterministic search model and using simulations of a stochastic version of the model. I show that a shock that changes average labor productivity primarily alters the present value of wages, generating only a small movement along a downward sloping Beveridge curve (unemploymentvacancy locus). A shock to the job destruction rate generates a counterfactually positive correlation between unemployment and vacancies. In both cases, the shock is only slightly amplified and the model exhibits virtually no propagation. I reconcile these findings with an existing literature and argue that the source of the model’s failure is lack of wage rigidity, a consequence of the assumption that wages are determined by Nash bargaining. ∗ This is a major revision of ‘Equilibrium Unemployment Fluctuations’. I thank Daron Acemoglu, Olivier
The Twin Crises: The Causes of Banking and BalanceofPayments Problems
"... In the wake of the Mexican and Asian currency turmoil, the subject of financial crises has come to the forefront of academic and policy discussions. This paper analyzes the links between banking and currency crises. We find that: problems in the banking sector typically precede a currency crisis—the ..."
Abstract

Cited by 890 (27 self)
 Add to MetaCart
In the wake of the Mexican and Asian currency turmoil, the subject of financial crises has come to the forefront of academic and policy discussions. This paper analyzes the links between banking and currency crises. We find that: problems in the banking sector typically precede a currency crisis—the currency crisis deepens the banking crisis, activating a vicious spiral; financial liberalization often precedes banking crises. The anatomy of these episodes suggests that crises occur as the economy enters a recession, following a prolonged boom in economic activity that was fueled by credit, capital inflows, and accompanied by an overvalued currency.
A Simple Model of Capital Market Equilibrium with Incomplete Information
 JOURNAL OF FINANCE
, 1987
"... The sphere of modern financial economics encompases finance, micro investment theory and much of the economics of uncertainty. As is evident from its influence on other branches of economics including public finance, industrial organization and monetary theory, the boundaries of this sphere are both ..."
Abstract

Cited by 720 (2 self)
 Add to MetaCart
The sphere of modern financial economics encompases finance, micro investment theory and much of the economics of uncertainty. As is evident from its influence on other branches of economics including public finance, industrial organization and monetary theory, the boundaries of this sphere are both permeable and flexible. The complex interactions of time and uncertainty guarantee intellectual challenge and intrinsic excitement to the study of financial economics. Indeed, the mathematics of the subject contain some of the most interesting applications of probability and optimization theory. But for all its mathematical refinement, the research has nevertheless had a direct and significant influence on practice. It was not always thus. Thirty years ago, finance theory was little more than a collection of anecdotes, rules of thumb, and manipulations of accounting data with an almost exclusive focus on corporate financial management. There is no need in this meeting of the guild to recount the subsequent evolution from this conceptual potpourri to a rigorous economic
Robust Monte Carlo Localization for Mobile Robots
, 2001
"... Mobile robot localization is the problem of determining a robot's pose from sensor data. This article presents a family of probabilistic localization algorithms known as Monte Carlo Localization (MCL). MCL algorithms represent a robot's belief by a set of weighted hypotheses (samples), whi ..."
Abstract

Cited by 826 (88 self)
 Add to MetaCart
Mobile robot localization is the problem of determining a robot's pose from sensor data. This article presents a family of probabilistic localization algorithms known as Monte Carlo Localization (MCL). MCL algorithms represent a robot's belief by a set of weighted hypotheses (samples), which approximate the posterior under a common Bayesian formulation of the localization problem. Building on the basic MCL algorithm, this article develops a more robust algorithm called MixtureMCL, which integrates two complimentary ways of generating samples in the estimation. To apply this algorithm to mobile robots equipped with range finders, a kernel density tree is learned that permits fast sampling. Systematic empirical results illustrate the robustness and computational efficiency of the approach.
Text Classification from Labeled and Unlabeled Documents using EM
 MACHINE LEARNING
, 1999
"... This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. This is important because in many text classification problems obtaining training labels is expensive, while large qua ..."
Abstract

Cited by 1033 (19 self)
 Add to MetaCart
This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. This is important because in many text classification problems obtaining training labels is expensive, while large quantities of unlabeled documents are readily available. We introduce an algorithm for learning from labeled and unlabeled documents based on the combination of ExpectationMaximization (EM) and a naive Bayes classifier. The algorithm first trains a classifier using the available labeled documents, and probabilistically labels the unlabeled documents. It then trains a new classifier using the labels for all the documents, and iterates to convergence. This basic EM procedure works well when the data conform to the generative assumptions of the model. However these assumptions are often violated in practice, and poor performance can result. We present two extensions to the algorithm that improve ...
Results 1  10
of
53,768