Mass shifting roles of negative kernel mass in density estimation

f(x) is a univariate density in C ⁴ with bounded support. For any n and sufficiently small kernel bandwidths, the symmetric appendage of any negative mass, –U, to any smooth unimodal symmetric kernel of order p=2 shifts expected estimator mass from regions where f(x)>0 to regions where f(x)<0. For large n, the mean automatic kernel adaptation induced by –U is analyzed in the simplest MISE reduction scenario: The symmetric appendage of –U to the uniform kernel K(x, X) over MISE-optimal bandwidths reduces MISE by shifting K(x, X) mass asymmetrically across the observation X in the direction of decreasing |f(x)|.     

Curvature and finite domination

Upper bounds obtained by Gromov on the Betti numbers of certain closed Riemannian manifolds are shown to be upper bounds on the minimum number of cells in --spaces dominating such manifolds.

     

Eclipsed Isopropyl Conformations of Two Dimeric Hydrazines

The X-ray structures of 4,10-di-tert-butyl-5,9-diisopropyl-4,5,9,10-tetraazatetracyclo[6.2.2.2(3,6)]tetradecane (s4iPr) and its 4,9-di-tert-butyl-5,10-diisopropyl isomer (a4iPr) are reported. Both compounds are in conformations having their in-N-alkyl groups (directed toward the central CH-CH bond of the molecule) anti to each other, as expected from previous work. The principal feature of interest is that one in-isopropyl group in each compound is in an eclipsed conformation, NN,C(alpha)Me twist angle -0.5(5) degrees for s4iPr and -6.4(4) degrees for a4iPr. Low energy (somewhat less) eclipsed in-isopropyl conformations are predicted by both molecular mechanics (MM2) and semiempirical quantum mechanical (AM1) calculations. The asymmetry of the potentially C(2) symmetric a4iPr because the two in-isopropyl groups are in different rotamers is apparently not a result of crystal packing forces, because a conformation with different isopropyl rotamers is the more stable one by at least 1.0 kcal/mol in solution, determined by (13)C-NMR spectroscopy. This result is not predicted by either calculation method. The "monomer", 2-tert-butyl-3-isopropyl-2,3-diazabicyclo[2.2.2]octane (3), proves to be a poor model for the conformations of 4iPr.