Support vector machines (SVMs) rely on the inherent geometry of a data set to classify training data. Because of this, we believe SVMs are an excellent candidate to guide the development of an analytic feature selection algorithm, as opposed to the more commonly used heuristic methods. We propose a filter-based feature selection algorithm based on the inherent geometry of a feature set. Through...

Assume that the learner observes a sequence of tasks in a fixed order, t1, ..., tn, with corresponding training sets, S1, ..., Sn, where Si = {(x1, y 1), ..., (ximi , y mi)} consists of mi i.i.d. samples from a task-specific data distribution Di. We assume that all tasks share the same input space X and output space Y and that the learner uses the same loss function l : Y × Y → [0, 1] and hypot...

Empirical studies have suggested that stock returns can be predicted by financial variables such as the dividend-price ratio. However, these studies typically ignore the high persistence of predictor variables, which can make first-order asymptotics a poor approximation in finite samples. Using a more accurate asymptotic approximation, we propose two methods to deal with the persistence problem...

We explore the ability to perform automatic prosodic analysis in one language using models trained on another. If we are successful, we should be able to identify prosodic elements in a language for which little or no prosodically labeled training data is available, using models trained on a language for which such training data exists. Given the laborious nature of manual prosodic annotation, ...

We consider using an ensemble of binary classifiers for transductive prediction, when unlabeled test data are known in advance. We derive minimax optimal rules for confidence-rated prediction in this setting. By using PAC-Bayes analysis on these rules, we obtain data-dependent performance guarantees without distributional assumptions on the data. Our analysis techniques are readily extended to ...

In this paper a class of semi-implicit predictor–corrector time integration schemes is proposed. Linear stability analysis is used to identify promising methods and these are applied to the nonlinear system of the shallow water equations on an icosahedral grid. The model used is a testbed for the future development of a more complete atmospheric model. Experiments with standard test cases from ...

Recently a new class of generalised diffusion filters called osmosis filters has been proposed. Osmosis models are useful for a variety of tasks in visual computing. In this paper, we show that these filters are also beneficial outside image processing and computer graphics: We exploit their use for the construction of better numerical schemes for hyperbolic partial differential equations that ...

In this work, we propose a predictor-corrector interior point method for linear programming in a primal-dual context, where the next iterate is chosen by the minimization of a polynomial merit function of three variables: the first is the steplength, the second defines the central path and the third models the weight of a corrector direction. The merit function minimization is performed by rest...

We discuss SPaRe: selective partial replication, a methodology for concurrent fault detection in finite state machine (FSMs). The proposed method is similar to duplication, wherein a replica of the circuit acts as a predictor that immediately detects errors by comparison to the original FSM. However, instead of duplicating the FSM, SPaRe selects a few prediction functions which only partially r...