Minimax rates for sparse multi-kernel classification via a new $\ell_1$-based SVM

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：chxiang007

【摘要】

：

This paper studies minimax rates of nonparametric classification under the framework of sparse support vector machine(SVM)with multiple kernels.

【作者】

：

Shaogao Lv

【机构】

：

Center of Statistics Research,Southwestern University of Finance and Economics

【出处】

：

上海交通大学

【发表日期】

：

2016年4期

下载到本地 , 更方便阅读

下载此文赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

　　This paper studies minimax rates of nonparametric classification under the framework of sparse support vector machine(SVM)with multiple kernels.

其他文献

Iterative Algorithms for Estimating High-dimensional Covariance Matrices

In this presentation,we talk about the shrinkage estimate for population covariance matrices with high-dimensional dimensions.

会议

Covariance matrix estimationhigh-dimensional dataiterative algorithms

A Quality Control Technique Applying to the Meteorological Observation Data

In general,the cluster analysis on the climatological data is useful method that the climate characteristic of South Korea is analyzed by clusters.

会议

meteorological observation datacluster analysis.K-means methodgrid dataquali

Dependent microstructure noise and integrated volatility estimation from high-frequency data

We develop econometric tools to study integrated volatility with potentially time-dependent microstructure noise in high-frequency data.

会议

Bi-power variationfinite sample bias correctionhigh-frequency datamarket micr

Identifying Causal Effects with Negative Controls

Suppose we are interested in a causal effect that is confounded by an unobserved variable.Suppose however one has available negative control outcomes that are not causally affected by the treatment,an

会议

ConfounderIdentificationNegative control

Geometrically Tempered Hamiltonian Monte Carlo

Hamiltonian Monte Carlo(HMC)has become routinely used for sampling from posterior distributions.Its extension Riemann manifold HMC(RMHMC)modifies the proposal kernel through distortion of local distan

会议

Bayesian inferenceHamiltonian dynamicsMarkov chain Monte CarloRiemannian geom

Bayesian Nonparametric Beta Regression for Longitudinal Data

In this paper we present an innovative non-parametric Bayesian approach to estimate and predict individual patient longitudinal biomarker distributions.

会议

Bayesian beta regressionFractional polynomialsLongitudinal analysisSubjectspe

A Novel Method on Next-Generation Data Normalization and Differentially-Expressed Gene Detection

Next generation sequencing(NGS)data contain measurement errors.Normalizing NGS data is challenging and crucial.We propose to normalize the NGS gene expression profiles via binning and density estimati

会议

BinningNon-parametric RegressionDensity EstimationGeneralized Lambda Distribu

Dempster-Shafer methods for one-and two-sample comparison of quantiles,with applications to HIV vacc

Here we introduce a new analytical method for testing the hypothesis that the medians of two distributions are equal or within some range of one another,given independent draws from each,or that the m

会议

Dempster-ShaferDSquantilenon-parametrichypothesis test

Rising Above Chaotic Likelihoods

Berliner(1991)identified a number of difficulties in using the likelihood function within the Bayesian paradigm for state estimation of chaotic systems.Even when the equations of the system are given,

会议

likelihoodchaotic systemimportance samplingdata assimilation

The control of the false discovery rate under structured hypotheses

Complex large-scale studies,such as those related to microarray and quantitative trait loci,often involve testing multiple hierarchically ordered hypotheses.

会议

False discovery ratehierarchical testingmultiple testingPRDS propertystepwis

Minimax rates for sparse multi-kernel classification via a new $\ell_1$-based SVM

其他学术论文