Unified approach to coefficient-based regularized regression
نویسندگان
چکیده
منابع مشابه
Unified approach to coefficient-based regularized regression
In this paper, we consider the coefficient-based regularized least-squares regression problem with the lq-regularizer (1 ≤ q ≤ 2) and data dependent hypothesis spaces. Algorithms in data dependent hypothesis spaces perform well with the property of flexibility. We conduct a unified error analysis by a stepping stone technique. An empirical covering number technique is also employed in our study...
متن کاملSimulation-based Regularized Logistic Regression
In this paper, we develop a simulation-based framework for regularized logistic regression, exploiting two novel results for scale mixtures of normals. By carefully choosing a hierarchical model for the likelihood by one type of mixture, and implementing regularization with another, we obtain new MCMC schemes with varying efficiency depending on the data type (binary v. binomial, say) and the d...
متن کاملHeritability Estimation using Regularized Regression Approach (HERRA)
Heritability is a concept that summarizes the proportion of phenotypic variance that is due to genetic factors, with broad-sense heritability referring to genetic variation that may include effects due to dominance and epistasis, and narrow-sense heritability referring to additive genetic variation. The popular GCTA software uses the random effects approach to estimate the narrow-sense heritabi...
متن کاملSketching for M-Estimators: A Unified Approach to Robust Regression
We give algorithms for the M-estimators minx ‖Ax− b‖G, where A ∈ Rn×d and b ∈ R, and ‖y‖G for y ∈ R n is specified by a cost function G : R 7→ R≥0, with ‖y‖G ≡ ∑ iG(yi). The M -estimators generalize `p regression, for which G(x) = |x|. We first show that the Huber measure can be computed up to relative error in O(nnz(A) logn + poly(d(log n)/ε)) time, where nnz(A) denotes the number of non-zero ...
متن کاملConvergence Rate of Coefficient Regularized Kernel-based Learning Algorithms
We investigate machine learning for the least square regression with data dependent hypothesis and coefficient regularization algorithms based on general kernels. We provide some estimates for the learning raters of both regression and classification when the hypothesis spaces are sample dependent. Under a weak condition on the kernels we derive learning error by estimating the rate of some K-f...
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: Computers & Mathematics with Applications
سال: 2011
ISSN: 0898-1221
DOI: 10.1016/j.camwa.2011.05.034