Minimax and Minimax Projection Designs Using Clustering
نویسندگان
چکیده
منابع مشابه
Minimax Gaussian Classification & Clustering
We present minimax bounds for classification and clustering error in the setting where covariates are drawn from a mixture of two isotropic Gaussian distributions. Here, we define clustering error in a discriminative fashion, demonstrating fundamental connections between classification (supervised) and clustering (unsupervised). For both classification and clustering, our lower bounds show that...
متن کاملExistence and symmetry of minimax regression designs
In this paper we address two important issues about minimax regression designs: existence and symmetry. These designs are robust against possible misspecification of the regression response. Existence is proved for A-optimal, D-optimal and Q-optimal minimax designs. Symmetry is proved for all D-optimal minimax designs and for some special cases of A-optimal and Q-optimal minimax designs.
متن کاملMinimax designs for approximately linear regression
We consider the approximately linear regression model E b 1x1 = I(x) 0 + f(x), XE S, where f(x) is a non-linear disturbance restricted only by a bound on its &(S) norm, and where S is the design space. For loss functions which are monotonic functions of the mean squared error matrix, we derive a theory to guide in the construction of designs which minimize the maximum (over f) loss. We then spe...
متن کاملMinimax design criterion for fractional factorial designs
An A-optimal minimax design criterion is proposed to construct fractional factorial designs, which extends the study of the D-optimal minimax design criterion in Lin and Zhou (Canadian Journal of Statistics 41, 325–340, 2013). The resulting Aoptimal and D-optimal minimax designs minimize, respectively, the maximum trace and determinant of the mean squared error matrix of the least squares estim...
متن کاملTwo-dimensional minimax Latin hypercube designs
We investigate minimax Latin hypercube designs in two dimensions for several distance measures. For the `-distance we are able to construct minimax Latin hypercube designs of n points, and to determine the minimal covering radius, for all n. For the `1-distance we have a lower bound for the covering radius, and a construction of minimax Latin hypercube designs for (infinitely) many values of n....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Computational and Graphical Statistics
سال: 2017
ISSN: 1061-8600,1537-2715
DOI: 10.1080/10618600.2017.1302881