搜索结果: 1-10 共查到“理论统计学 Minimization”相关记录10条 . 查询时间(0.06 秒)
Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
Stochastic Dual Coordinate Ascent Methods Regularized Loss Minimization
font style='font-size:12px;'>
2012/11/22
Stochastic Gradient Descent (SGD) has become popular for solving large scale supervised machine learning optimization problems such as SVM, due to their strong theoretical guarantees. While the closel...
Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
Stochastic Dual Coordinate Ascent Methods Regularized Loss Minimization
font style='font-size:12px;'>
2012/11/22
Stochastic Gradient Descent (SGD) has become popular for solving large scale supervised machine learning optimization problems such as SVM, due to their strong theoretical guarantees. While the closel...
Robust approachability and regret minimization in games with partial monitoring
Robust approachability regret games partial monitoring
font style='font-size:12px;'>
2011/6/20
Approachability has become a standard tool in analyzing learning algorithms in the adversarial
online learning setup. We develop a variant of approachability for games where there is ambiguity
in th...
Complexity of Unconstrained L_2-L_p Minimization
Nonsmooth optimization nonconvex optimization variable selection sparse solution reconstruction bridge estimator
font style='font-size:12px;'>
2011/6/21
We consider the unconstrained L2-Lp minimization: find a minimizer of kAx−bk2
2+λkxkp
p
for given A ∈ Rm×n, b ∈ Rm and parameters λ > 0, p ∈ [0, 1). This problem has been
studied extensively...
Sharper lower bounds on the performance of the empirical risk minimization algorithm
empirical risk minimization learning theory lower bound multidimensional central limit theorem uniform central limit theorem
font style='font-size:12px;'>
2011/3/24
We present an argument based on the multidimensional and the uniform central limit theorems, proving that, under some geometrical assumptions between the target function $T$ and the learning class $F$...
Probabilistic Recovery of Multiple Subspaces in Point Clouds by Geometric lp Minimization
Detection and clustering of subspaces in point clouds hybrid linear modeling lp minimizationas relaxation for l0 minimization
font style='font-size:12px;'>
2010/3/10
We assume data independently sampled froma mixture distribution on the unit ball of RD withK+1
components: the first component is a uniform distribution on that ball representing outliers and the oth...
Empirical risk minimization in inverse problems
Deconvolution empirical risk minimization multivariate density estimation nonparametric function estimation Radon transform tomography
font style='font-size:12px;'>
2010/3/9
We study estimation of a multivariate function f :Rd
!R when
the observations are available from the function Af, where A is a
known linear operator. Both the Gaussian white noise model and
densit...
Extension of Lipschitz integrands and minimization of nonconvex integral functionals. Applications to the optimal recourse problem in discrete time
Extension of Lipschitz integrands minimization of nonconvex integral functionals
font style='font-size:12px;'>
2009/9/24
Extension of Lipschitz integrands and minimization of nonconvex integral functionals. Applications to the optimal recourse problem in discrete time。
Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
rank convex optimization matrix norms random matrices compressed sensing semidefinite program-ming
font style='font-size:12px;'>
2010/4/29
The ane rank minimization problem consists of finding a matrix of minimum rank that
satisfies a given system of linear equality constraints. Such problems have appeared in the literature
of a divers...
Suboptimality of Penalized Empirical Risk Minimization in Classification
Suboptimality Penalized Empirical Risk Minimization Classification
font style='font-size:12px;'>
2010/4/27
Let F be a set of M classification procedures with values in
[−1, 1]. Given a loss function, we want to construct a procedure which
mimics at the best possible rate the best procedure in F. Th...