Kernel density construction using orthogonal forward regression

An automatic algorithm is derived for constructing kernel density estimates based on a regression approach that directly optimizes generalization capability. Computational efficiency of the density construction is ensured using an orthogonal forward regression, and the algorithm incrementally minimizes the leave-one-out test score. Local regularization is incorporated into the density construction process to further enforce sparsity. Examples are included to demonstrate the ability of the proposed algorithm to effectively construct a very sparse kernel density estimate with comparable accuracy to that of the full sample Parzen window density estimate.

Sparse kernel density construction using orthogonal forward regression with leave-one-out test score and local regularization

This paper presents an efficient construction algorithm for obtaining sparse kernel density estimates based on a regression approach that directly optimizes model generalization capability. Computational efficiency of the density construction is ensured using an orthogonal forward regression, and the algorithm incrementally minimizes the leave-one-out test score. A local regularization method is incorporated naturally into the density construction process to further enforce sparsity. An additional advantage of the proposed algorithm is that it is fully automatic and the user is not required to specify any criterion to terminate the density construction procedure. This is in contrast to an existing state-of-art kernel density estimation method using the support vector machine (SVM), where the user is required to specify some critical algorithm parameter. Several examples are included to demonstrate the ability of the proposed algorithm to effectively construct a very sparse kernel density estimate with comparable accuracy to that of the full sample optimized Parzen window density estimate. Our experimental results also demonstrate that the proposed algorithm compares favorably with the SVM method, in terms of both test accuracy and sparsity, for constructing kernel density estimates.

An orthogonal forward regression technique for sparse kernel density estimation

Using the classical Parzen window (PW) estimate as the desired response, the kernel density estimation is formulated as a regression problem and the orthogonal forward regression technique is adopted to construct sparse kernel density (SKD) estimates. The proposed algorithm incrementally minimises a leave-one-out test score to select a sparse kernel model, and a local regularisation method is incorporated into the density construction process to further enforce sparsity. The kernel weights of the selected sparse model are finally updated using the multiplicative nonnegative quadratic programming algorithm, which ensures the nonnegative and unity constraints for the kernel weights and has the desired ability to reduce the model size further. Except for the kernel width, the proposed method has no other parameters that need tuning, and the user is not required to specify any additional criterion to terminate the density construction procedure. Several examples demonstrate the ability of this simple regression-based approach to effectively construct a SKID estimate with comparable accuracy to that of the full-sample optimised PW density estimate. (c) 2007 Elsevier B.V. All rights reserved.

A forward-constrained regression algorithm for sparse kernel density estimation

Using the classical Parzen window (PW) estimate as the target function, the sparse kernel density estimator is constructed in a forward-constrained regression (FCR) manner. The proposed algorithm selects significant kernels one at a time, while the leave-one-out (LOO) test score is minimized subject to a simple positivity constraint in each forward stage. The model parameter estimation in each forward stage is simply the solution of jackknife parameter estimator for a single parameter, subject to the same positivity constraint check. For each selected kernels, the associated kernel width is updated via the Gauss-Newton method with the model parameter estimate fixed. The proposed approach is simple to implement and the associated computational cost is very low. Numerical examples are employed to demonstrate the efficacy of the proposed approach.

Hydrogen bond-induced pair formation of glycine on the chiral Cu{531} surface

Enantio-specific interactions on intrinsically chiral or chirally modified surfaces can be identified experimentally via comparison of the adsorption geometries of similar nonchiral and chiral molecules. Information about the effects of substrate-related and in interactions on the adsorption geometry of glycine, the only natural nonchiral amino acid, is therefore important for identifying enantio-specific interactions of larger chiral amino acids. We have studied the long- and short-range adsorption geometry and bonding properties of glycine on the intrinsically chiral Cu{531} surface with low-energy electron diffraction, near-edge X-ray absorption One structure spectroscopy, X-ray photoelectron spectroscopy, and temperature-programmed desorption. For coverages between 0.15 and 0.33 ML (saturated chemisorbed layer) and temperatures between 300 and 430 K, glycine molecules adsorb in two different azimuthal orientations, which are associated with adsorption sites on the {110} and {311} microfacets of Cu{531}. Both types of adsorption sites allow a triangular footprint with surface bonds through the two oxygen atoms and the nitrogen atom. The occupation of the two adsorption sites is equal for all coverages, which can be explained by pair formation due to similar site-specific adsorption energies and the possibility of forming hydrogen bonds between molecules on adjacent {110} and {311} sites. This is not the ease for alanine and points toward higher site specificity in the case of alanine, which is eventually responsible for the enantiomeric differences observed for the alanine system.

Sparse kernel density estimation technique based on zero-norm constraint

A sparse kernel density estimator is derived based on the zero-norm constraint, in which the zero-norm of the kernel weights is incorporated to enhance model sparsity. The classical Parzen window estimate is adopted as the desired response for density estimation, and an approximate function of the zero-norm is used for achieving mathemtical tractability and algorithmic efficiency. Under the mild condition of the positive definite design matrix, the kernel weights of the proposed density estimator based on the zero-norm approximation can be obtained using the multiplicative nonnegative quadratic programming algorithm. Using the -optimality based selection algorithm as the preprocessing to select a small significant subset design matrix, the proposed zero-norm based approach offers an effective means for constructing very sparse kernel density estimates with excellent generalisation performance.

Probability density estimation with tunable kernels using orthogonal forward regression

A generalized or tunable-kernel model is proposed for probability density function estimation based on an orthogonal forward regression procedure. Each stage of the density estimation process determines a tunable kernel, namely, its center vector and diagonal covariance matrix, by minimizing a leave-one-out test criterion. The kernel mixing weights of the constructed sparse density estimate are finally updated using the multiplicative nonnegative quadratic programming algorithm to ensure the nonnegative and unity constraints, and this weight-updating process additionally has the desired ability to further reduce the model size. The proposed tunable-kernel model has advantages, in terms of model generalization capability and model sparsity, over the standard fixed-kernel model that restricts kernel centers to the training data points and employs a single common kernel variance for every kernel. On the other hand, it does not optimize all the model parameters together and thus avoids the problems of high-dimensional ill-conditioned nonlinear optimization associated with the conventional finite mixture model. Several examples are included to demonstrate the ability of the proposed novel tunable-kernel model to effectively construct a very compact density estimate accurately.

Regression based D-optimality experimental design for sparse kernel density estimation

This paper derives an efficient algorithm for constructing sparse kernel density (SKD) estimates. The algorithm first selects a very small subset of significant kernels using an orthogonal forward regression (OFR) procedure based on the D-optimality experimental design criterion. The weights of the resulting sparse kernel model are then calculated using a modified multiplicative nonnegative quadratic programming algorithm. Unlike most of the SKD estimators, the proposed D-optimality regression approach is an unsupervised construction algorithm and it does not require an empirical desired response for the kernel selection task. The strength of the D-optimality OFR is owing to the fact that the algorithm automatically selects a small subset of the most significant kernels related to the largest eigenvalues of the kernel design matrix, which counts for the most energy of the kernel training data, and this also guarantees the most accurate kernel weight estimate. The proposed method is also computationally attractive, in comparison with many existing SKD construction algorithms. Extensive numerical investigation demonstrates the ability of this regression-based approach to efficiently construct a very sparse kernel density estimate with excellent test accuracy, and our results show that the proposed method compares favourably with other existing sparse methods, in terms of test accuracy, model sparsity and complexity, for constructing kernel density estimates.

Low-lying excited states and primary photoproducts of [Os-3(CO)(10)-(s-cis-L)] (L = cyclohexa-1,3-diene, buta-1,3-diene)] clusters studied by picosecond time-resolved UV/Vis and IR spectroscopy and by density functional theory

Combined picosecond transient absorption and time-resolved infrared studies were performed, aimed at characterising low-lying excited states of the cluster [Os-3(CO)(10)(s-cis-L)] (L= cyclohexa-1,3-diene, 1) and monitoring the formation of its photoproducts. Theoretical (DFT and TD-DFT) calculations on the closely related cluster with L=buta-1,3-diene (2') have revealed that the low-lying electronic transitions of these [Os-3(CO)(10)(s-cis-1,3-diene)] clusters have a predominant sigma(core)pi*(CO) character. From the lowest sigmapi* excited state, cluster 1 undergoes fast Os-Os(1,3-diene) bond cleavage (tau=3.3 ps) resulting in the formation of a coordinatively unsaturated primary photoproduct (1a) with a single CO bridge. A new insight into the structure of the transient has been obtained by DFT calculations. The cleaved Os-Os(1,3-diene) bond is bridged by the donor 1,3-diene ligand, compensating for the electron deficiency at the neighbouring Os centre. Because of the unequal distribution of the electron density in transient la, a second CO bridge is formed in 20 ps in the photoproduct [Os-3(CO)(8)(mu-CO)(2)- (cyclohexa-1,3-diene)] (1b). The latter compound, absorbing strongly around 630 nm, mainly regenerates the parent cluster with a lifetime of about 100 ns in hexane. Its structure, as suggested by the DFT calculations, again contains the 1,3-diene ligand coordinated in a bridging fashion. Photoproduct 1b can therefore be assigned as a high-energy coordination isomer of the parent cluster with all Os-Os bonds bridged.

Strongly nucleophilic RhI centre in square-planar complexes with terdentate (κ3) 2,2′:6′,2′′-terpyridine ligands: crystallographic, electrochemical and density functional theoretical studies

Rh-I-terpyridine complexes have been unambiguously formed for the first time. The 2,21:6',2"-terpyridine (tpy), 4'-chloro-2,2':6',2"-terpyridine (4'-Cl-tpy) and 4'-(tert-butyldimethylsilyl-ortho-carboranyl)-2,2':6',2"-terpyridine (carboranyl-tpy) ligands were used for successful syntheses and characterisation of the corresponding Rh-I complexes with halide coligands, [Rh(X)(4'-Y-terpyridine)] (X = Cl, Y = H, Cl, carboranyl; X = Br, Y = H). All four neutral Rh-tpy complexes are square planar, with Rh-X bonds in the plane of the 4'-Y-terpyridine ligands. Full characterisation of these dark blue, highly air-sensitive compounds was hampered by their poor solubility in various organic solvents. This is mainly due to the formation of pi-stacked aggregates, as evidenced by the crystal structure of [Rh(Cl)(tpy)]; in addition, [Rh(Cl)(carboranyl-tpy)] merely forms discrete dimers. The (bonding) properties of the novel Rh-I-terpyridine complexes have been studied with single-crystal X-ray diffraction, (time-dependent) density functional theoretical (DFT) calculations, far-infrared spectroscopy, electronic absorption spectroscopy and cyclic voltammetry. From DFT calculations, the HOMO of the studied Rh-I-terpyridine complexes involves predominantly the metal centre, while the LUMO resides on the terpyridine ligand. Absorption bands of the studied complexes in the visible region (400-900 nm) can be assigned to MLCT and MLCT/XLCT transitions. The relatively low oxidation potentials of [Rh(X)(tpy)] (X = Cl, Br) point to a high electron density on the metal centre. This makes the Rh-I-terpyridine complexes strongly nucleophilic and (potentially) highly reactive towards various (small) substrate molecules containing carbon-halide bonds.

Inter-relationships between small, dense low-density lipoprotein (LDL), plasma triacylglycerol and LDL apoprotein B in an atherogenic lipoprotein phenotype in free-living subjects

A predominance of small, dense low-density lipoprotein (LDL) is a major component of an atherogenic lipoprotein phenotype, and a common, but modifiable, source of increased risk for coronary heart disease in the free-living population. While much of the atherogenicity of small, dense LDL is known to arise from its structural properties, the extent to which an increase in the number of small, dense LDL particles (hyper-apoprotein B) contributes to this risk of coronary heart disease is currently unknown. This study reports a method for the recruitment of free-living individuals with an atherogenic lipoprotein phenotype for a fish-oil intervention trial, and critically evaluates the relationship between LDL particle number and the predominance of small, dense LDL. In this group, volunteers were selected through local general practices on the basis of a moderately raised plasma triacylglycerol (triglyceride) level (>1.5 mmol/l) and a low concentration of high-density-lipoprotein cholesterol (<1.1 mmol/l). The screening of LDL subclasses revealed a predominance of small, dense LDL (LDL subclass pattern B) in 62% of the cohort. As expected, subjects with LDL subclass pattern B were characterized by higher plasma triacylglycerol and lower high-density lipoprotein cholesterol (<1.1 mmol/l) levels and, less predictably, by lower LDL cholesterol and apoprotein B levels (P<0.05; LDL subclass A compared with subclass B). While hyper-apoprotein B was detected in only five subjects, the relative percentage of small, dense LDL-III in subjects with subclass B showed an inverse relationship with LDL apoprotein B (r=-0.57; P<0.001), identifying a subset of individuals with plasma triacylglycerol above 2.5 mmol/l and a low concentration of LDL almost exclusively in a small and dense form. These findings indicate that a predominance of small, dense LDL and hyper-apoprotein B do not always co-exist in free-living groups. Moreover, if coronary risk increases with increasing LDL particle number, these results imply that the risk arising from a predominance of small, dense LDL may actually be reduced in certain cases when plasma triacylglycerol exceeds 2.5 mmol/l.