基于半参数Copula学习的确定性独立筛选研究

This paper is concerned with ultrahigh dimensional data analysis,which has become increasingly important in diverse scientific fields.We develop a sure independence screening procedure via the measure of conditional mean dependence based on Copula(CC-SIS,for short).The CC-SIS can be implemented as easily as the sure independence screening procedures which respectively based on the Pearson correlation,conditional mean and distance correlation(SIS,SIRS and DC-SIS,for short)and can significantly improve the performance of feature screening.We establish the sure screening property for the CC-SIS,and conduct simulations to examine its finite sample performance.Numerical comparison indicates that the CC-SIS performs better than the other two methods in various models.At last,we also illustrate the CC-SIS through a real data example.

The Dependence of Chimera States on Initial Conditions

A chimera state consisting of both coherent and incoherent groups is a fascinating spatial pattern in non-locally coupled identical oscillators. It is thought that random initial conditions hardly evolve to chimera states. In this work, we study the dependence of chimera states on initial conditions. We show that random initial conditions may lead to chimera states and the chance of realizing chimera states becomes increasing when the model parameters axe moving away from the boundary of their stable regime.

The central limit theorem and chaos

Let X be a compact metric space studies some relationships between stochastic and f ： X→ X be a continuous map. This paper and topological properties of dynamical systems. It is shown that if f satisfies the central limit theorem, then f is topologically ergodic and / is sensitively dependent on initial conditions if and only if / is neither minimal nor equicontinuous.

Discovering context-aware conditional functional dependencies

Conditional functional dependencies（CFDs） are important techniques for data consistency. However, CFDs are limited to 1） provide the reasonable values for consistency repairing and 2） detect potential errors. This paper presents context-aware conditional functional dependencies（CCFDs） which contribute to provide reasonable values and detect po- tential errors. Especially, we focus on automatically discov- ering minimal CCFDs. In this paper, we present context rela- tivity to measure the relationship of CFDs. The overlap of the related CFDs can provide reasonable values which result in more accuracy consistency repairing, and some related CFDs are combined into CCFDs. Moreover, we prove that discover- ing minimal CCFDs is NP-complete and we design the pre- cise method and the heuristic method. We also present the dominating value to facilitate the process in both the precise method and the heuristic method. Additionally, the context relativity of the CFDs affects the cleaning results. We will give an approximate threshold of context relativity accord- ing to data distribution for suggestion. The repairing results are approved more accuracy, even evidenced by our empirical evaluation.

Conditional mean convergence theorems of conditionally dependent random variables under conditions of integrability

We give the conditionally residual h-integrability with exponent r for an array of random variables and establish the conditional mean convergence of conditionally negatively quadrant dependent and conditionally negative associated random variables under this integrability. These results generalize and improve the known ones.

Recent Development of Chaos Theory in Topological Dynamics

We give a summary on the recent development of chaos theory in topological dynamics, focusing on Li-Yorke chaos, Devaney chaos, distributional chaos, positive topological entropy, weakly mixing sets and so on, and their relationships.

Mating behavior as an indicator of quality of Drosophila subobscura males？

According to current theoretical predictions, any deleterious mutations that reduce nonsexual fitness may have a negative influence on mating success. This means that sexual selection may remove deleterious mutations from the populations. Males of good genetic quality should be more successful in mating, compared to the males of lower genetic quality. As mating success is a condition dependent trait, large fractions of the genome may be a target of sexual selection and many behavioral traits are likely to be condition dependent. We manipulated the genetic quality of Drosophila subobscura males by inducing mutations with ionizing radiation and observed the effects of the obtained heterozygous mutations on male mating behavior： courtship occurrence, courtship latency, mating occurrence, latency to mating and duration of mating. We found possible effects of mutations. Females mated more frequently with male progeny of nonirradiated males and that these males courted females faster compared to the male progeny of irradiated males. Our findings indicate a possible important role of sexual selection in purging deleterious mutations.

On the Hochstadt–Lieberman Theorem for Discontinuous Boundary-valued Problems

In this paper, we discuss the half inverse problem for Sturm–Liouville equations with boundary conditions dependent on the spectral parameter and a finite number of discontinuities inside the interval and prove the Hochstadt–Liberman type theorem for the above boundary-valued problem.