Results 1  10
of
17
Sequential auctions for the allocation of resources with complementarities
, 1999
"... Marketbased mechanisms such as auctions are being studied as an appropriate means for resource allocation in distributed and inultiagcnl decision problems. When agents value resources in combination rather than in isolation, one generally relies on combinatorial auctions where agents bid tor resour ..."
Abstract

Cited by 85 (2 self)
 Add to MetaCart
Marketbased mechanisms such as auctions are being studied as an appropriate means for resource allocation in distributed and inultiagcnl decision problems. When agents value resources in combination rather than in isolation, one generally relies on combinatorial auctions where agents bid tor resource bundles. or simultaneous auctions for all resources. We develop a different model, where agents bid for required resources sequentially. This model has the advantage that it can be applied in settings where combinatorial and simultaneous models are infeasible (e.g.. when resources are made available at different points in time by different parties), as well as certain benefits in settings where combinatorial models are applicable. We develop a dynamic programming model tor agents to compute bidding policies based on estimated distributions over prices. We also describe how these distributions are updated to provide a learning model for bidding behavior. 1
Local Learning in Probabilistic Networks With Hidden Variables
, 1995
"... Probabilistic networks, which provide compact descriptions of complex stochastic relationships among several random variables, are rapidly becoming the tool of choice for uncertain reasoning in artificial intelligence. We show that networks with fixed structure containing hidden variables can be lea ..."
Abstract

Cited by 77 (4 self)
 Add to MetaCart
Probabilistic networks, which provide compact descriptions of complex stochastic relationships among several random variables, are rapidly becoming the tool of choice for uncertain reasoning in artificial intelligence. We show that networks with fixed structure containing hidden variables can be learned automatically from data using a gradientdescent mechanism similar to that used in neural networks. We also extend the method to networks with intensionally represented distributions, including networks with continuous variables and dynamic probabilistic networks. Because probabilistic networks provide explicit representations of causal structure, human experts can easily contribute prior knowledge to the training process, thereby significantly improving the learning rate. Adaptive probabilistic networks (APNs) may soon compete directly with neural networks as models in computational neuroscience as well as in industrial and financial applications. 1 Introduction Intelligent systems, ...
Object Class Recognition with Many Local Features
"... In this paper we present a method to recognize an object class by learning a statistical model of the class. The probabilistic model decomposes the appearance of an object class into a set of local parts and models the appearance, relative location, cooccurrence, and scale of these parts. However, ..."
Abstract

Cited by 9 (0 self)
 Add to MetaCart
In this paper we present a method to recognize an object class by learning a statistical model of the class. The probabilistic model decomposes the appearance of an object class into a set of local parts and models the appearance, relative location, cooccurrence, and scale of these parts. However, in many object classification approaches that use local features, learning the parameters is exponential in the number of parts because of the problem of matching local features in the image to parts in the model. In this paper we present a learning method that overcomes this difficulty by adding new parts to the model incrementally, using the MaximumLikelihood framework. When we add a part to the model, a set of candidate parts are selected and the part that increases the likelihood of the data the most is added to the model. Once this part is added to the model, the parameters for all parts up to this point are updated using EM. The learning and recognition in this approach are translation and scale invariant, robust to background clutter, and has less restriction on the number of parts in the model. The validity of the approach is demonstrated on a real world dataset, where the approach is competitive with others, and where the learning for a rich model is much faster than previous approaches.
Shape Matching and Registration by Datadriven EM
, 2007
"... In this paper, we present an efficient and robust algorithm for shape matching, registration, and detection. The task is to geometrically transform a source shape to fit a target shape. The measure of similarity is defined in terms of the amount of transformation required. The shapes are represented ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
In this paper, we present an efficient and robust algorithm for shape matching, registration, and detection. The task is to geometrically transform a source shape to fit a target shape. The measure of similarity is defined in terms of the amount of transformation required. The shapes are represented by sparsepoint or continuouscontour representations depending on the form of the data. We formulate the problem as probabilistic inference using a generative model and the EM algorithm. But this algorithm has problems with initialization and computing the Estep. To address these problems, we define a discriminative model which makes use of shape features. This gives a hybrid algorithm which combines the generative and discriminative models. The resulting algorithm is very fast, due to the effectiveness of shapefeatures for solving correspondence requiring typically only four iterations. The convergence time of the algorithm is under a second. We demonstrate the effectiveness of the algorithm by testing it on standard datasets, such as MPEG7, for shape matching and by applying it to a range of matching, registration, and foreground/background segmentation problems.
On Variational Message Passing on Factor Graphs
, 2007
"... In this paper, it is shown how (naive and structured) variational algorithms may be derived from a factor graph by mechanically applying generic message computation rules; in this way, one can bypass errorprone variational calculus. In prior work by Bishop et al., Xing et al., and Geiger, directed ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
In this paper, it is shown how (naive and structured) variational algorithms may be derived from a factor graph by mechanically applying generic message computation rules; in this way, one can bypass errorprone variational calculus. In prior work by Bishop et al., Xing et al., and Geiger, directed and undirected graphical models have been used for this purpose. The factor graph notation amounts to simpler generic variational message computation rules; by means of factor graphs, variational methods can straightforwardly be compared to and combined with various other messagepassing inference algorithms, e.g., Kalman filters and smoothers, iterated conditional modes, expectation maximization (EM), gradient methods, and particle filters. Some of those combinations have been explored in the literature, others seem to be new. Generic message computation rules for such combinations are formulated. 1.
Steepest Descent as Message Passing
"... Abstract — It is shown how steepest descent (or steepest ascent) may be viewed as a message passing algorithm with “local ” message update rules. For example, the wellknown backpropagation algorithm for the training of feedforward neural networks may be viewed as message passing on a factor graph. ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
Abstract — It is shown how steepest descent (or steepest ascent) may be viewed as a message passing algorithm with “local ” message update rules. For example, the wellknown backpropagation algorithm for the training of feedforward neural networks may be viewed as message passing on a factor graph. The factor graph approach with its emphasis on “local ” computations makes it easy to combine steepest descent with other message passing algorithms such as the sum/maxproduct algorithms, expectation maximization, Kalman filtering/smoothing, and particle filters. As an example, parameter estimation in a state space model is considered. For this example, it is shown how steepest descent can be used for the maximization step in expectation maximization.
Adaptive dimension reduction for clustering high dimensional data
"... Abstract It is wellknown that for high dimensional data clustering, standard algorithms such as EM and the Kmeansare often trapped in local minimum. Many initialization methods were proposed to tackle this problem, but with only limited success. In this paper we propose a newapproach to resolve t ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Abstract It is wellknown that for high dimensional data clustering, standard algorithms such as EM and the Kmeansare often trapped in local minimum. Many initialization methods were proposed to tackle this problem, but with only limited success. In this paper we propose a newapproach to resolve this problem by repeated dimension reductions such that Kmeans or EM are performedonly in very low dimensions. Cluster membership is utilized as a bridge between the reduced dimensional subspace and the original space, providing flexibility and ease of implementation. Clustering analysis performedon highly overlapped Gaussians, DNA gene expression profiles and internet newsgroups demonstrate the effectiveness of the proposed algorithm. 1 Introduction In many application areas, such as information retrieval, image processing, computational biology and global climate research, analysis of high dimensional datasets is frequently encountered. For example, in text processing, typical dimension of a word vector is of the size of the vocabulary of a document collection and tensof thousands of words/phrases are used routinely; in molecular biology, human gene expression profile analysis typically involves thousands of genes; and in image processing, a typical 2dim image has 1282 = 16,384 pixels or dimensions.
Clustering of HighDimensional and Correlated Data
"... Abstract Finite mixture models are being commonly used in a wide range of applications in practice concerning density estimation and clustering. An attractive feature of this approach to clustering is that it provides a sound statistical framework in which to assess the important question of how man ..."
Abstract
 Add to MetaCart
Abstract Finite mixture models are being commonly used in a wide range of applications in practice concerning density estimation and clustering. An attractive feature of this approach to clustering is that it provides a sound statistical framework in which to assess the important question of how many clusters there are in the data and their validity. We consider the applications of normal mixture models to highdimensional data of a continuous nature. One way to handle the fitting of normal mixture models is to adopt mixtures of factor analyzers. However, for extremely highdimensional data, some variablereduction method needs to be used in conjunction with the latter model such as with the procedure called EMMIXGENE. It was developed for the clustering of microarray data in bioinformatics, but is applicable to other types of data. We shall also consider the mixture procedure EMMIXWIRE (based on mixtures of normal components with random effects), which is suitable for clustering highdimensional data that may be structured (correlated and and replicated) as in longitudinal studies. 1
SPARLS: The Sparse RLS Algorithm
, 2010
"... We develop a Recursive L1Regularized Least Squares (SPARLS) algorithm for the estimation of a sparse tapweight vector in the adaptive filtering setting. The SPARLS algorithm exploits noisy observations of the tapweight vector output stream and produces its estimate using an ExpectationMaximizati ..."
Abstract
 Add to MetaCart
We develop a Recursive L1Regularized Least Squares (SPARLS) algorithm for the estimation of a sparse tapweight vector in the adaptive filtering setting. The SPARLS algorithm exploits noisy observations of the tapweight vector output stream and produces its estimate using an ExpectationMaximization type algorithm. We prove the convergence of the SPARLS algorithm to a nearoptimal estimate in a stationary environment and present analytical results for the steady state error. Simulation studies in the context of channel estimation, employing multipath wireless channels, show that the SPARLS algorithm has significant improvement over the conventional widelyused Recursive Least Squares (RLS) algorithm in terms of mean squared error (MSE). Moreover, these simulation studies suggest that the SPARLS algorithm (with slight modifications) can operate with lower computational requirements than the RLS algorithm, when applied to tapweight vectors with fixed support.