We have developed a high level library, the Nearest Neighbor Tool (NNT), to facilitate the coding of finite difference approximation weather prediction models on parallel computers. NNT provides portability and ease of programming and at the same time optimizes performance by allowing the overlap of computation and communication to tolerate the latency of remote data moves. In this paper we des...

In this paper we propose an approximated structured prediction framework for large scale graphical models and derive message-passing algorithms for learning their parameters efficiently. We first relate CRFs and structured SVMs and show that in CRFs a variant of the log-partition function, known as the soft-max, smoothly approximates the hinge loss function of structured SVMs. We then propose a...

This paper addresses a central problem of Bioinformatics and Proteomics: estimating the amounts of each of the thousands of proteins in a cell culture or tissue sample. Although laboratory methods involving isotopes have been developed for this problem, we seek a simpler method, one that uses fewer laboratory procedures. Specifically, our aim is to use data-mining methods to infer protein level...

We develop approximation algorithms for reducing expected classification cost, when there is a cost associated with obtaining the value of each attribute, and we are doing classification based on an ensemble of linear threshold classifiers. We focus on the stochastic setting where attribute values are independent, and their distributions are given. We review related work based on reductions to ...

Recent machine learning methods for sequential behavior prediction estimate the motives of behavior rather than the behavior itself. This higher-level abstraction improves generalization in different prediction settings, but computing predictions often becomes intractable in large decision spaces. We propose the Softstar algorithm, a softened heuristic-guided search technique for the maximum en...

A simplified model of the moist axisymmetric Hadley circulation is examined in the asymptotic limit in which surface drag is strong and the meridional wind is weak compared to the zonal wind. Our model consists of the quasi-equilibrium tropical circulation model (QTCM) equations on an axisymmetric aquaplanet equatorial beta-plane. This model includes two vertical momentum modes, one baroclinic ...

Neighborhood subspace approximation method has been developed for solving the property prediction problem. In this paper the performance of this method is evaluated on three groups of compounds. The molecular structure was encoded as sequences of well-known structural (topological) indices. Euclidean distance has been used for determining the similarities between compounds. Property prediction ...

A new wide-angle (WA) beam propagation method (BPM) is developed whereby the exact scalar Helmholtz propagator is replaced by any one of a sequence of higher-order m ,n Padé approximant operators. Unlike the previous well-known WA-BPM proposed by Hadley [Opt. Lett. 17, 1426 (1992)], the resulting formulations allow one a direct solution of the second-order scalar wave equation without having to...

The most common forecasting methods in business are based on exponential smoothing, and the most common time series in business are inherently non-negative. Therefore it is of interest to consider the properties of the potential stochastic models underlying exponential smoothing when applied to non-negative data. We explore exponential smoothing state space models for non-negative data under va...