Filters








638 Hits in 2.0 sec

Variable Selection and Regularization via Arbitrary Rectangle-range Generalized Elastic Net [article]

Yujia Ding, Qidi Peng, Zhengming Song, Hansen Chen
2021 arXiv   pre-print
Finally an application of S P 500 index tracking with constraints on the stock allocations is performed to provide general guidance for adapting ARGEN to solve real-world problems.  ...  As a natural extension of the nonnegative elastic net penalty method, ARGEN is proved to have variable selection consistency and estimation consistency under some conditions.  ...  Applied Mathe- matics and Computation, 227:541–552, 2014. [29] Lan Wu, Yuehan Yang, and Hanzhong Liu. Nonnegative-lasso and application in index tracking.  ... 
arXiv:2112.07785v1 fatcat:y7ocltjidbebxheqghft75hcvy

Penalized and constrained LAD estimation in fixed and high dimension

Xiaofei Wu, Rongmei Liang, Hu Yang
2021 Statistical Papers  
Simulation and application to real data also confirm that proposed estimation is an effective alternative when constrained lasso is unreliable.  ...  Recently, many literatures have proved that prior information and structure in many application fields can be formulated as constraints on regression coefficients.  ...  In SSE 50 index tracking, we select 5, 10 and 20 component stocks respectively, and in CSI 300 index, we select 25, 30 and 40 component stocks.  ... 
doi:10.1007/s00362-021-01229-0 pmid:33814727 pmcid:PMC8009762 fatcat:tvr2dnb6yjdvrf2oqmrti4mvqq

RLS-weighted Lasso for adaptive estimation of sparse signals

Daniele Angelosante, Georgios B. Giannakis
2009 2009 IEEE International Conference on Acoustics, Speech and Signal Processing  
The batch least-absolute shrinkage and selection operator (Lasso) has well-documented merits for estimating sparse signals of interest emerging in various applications, where observations adhere to parsimonious  ...  Simulated tests compare competing alternatives and corroborate the performance of the novel algorithms in estimating time-invariant and tracking slow-varying signals under sparsity constraints.  ...  Such a shortcoming was recently overcome for the batch Lasso by [11, 12] , and motivates the novel RLS-weighted Lasso approach outlined next for adaptive estimation and tracking applications involving  ... 
doi:10.1109/icassp.2009.4960316 dblp:conf/icassp/AngelosanteG09 fatcat:vnxfejn3gndkpoxxh4yewrdyja

The heterogeneous feature selection with structural sparsity for multimedia annotation and hashing: a survey

Fei Wu, Yahong Han, Xiang Liu, Jian Shao, Yueting Zhuang, Zhongfei Zhang
2012 International Journal of Multimedia Information Retrieval  
This paper introduces many of the recent efforts in sparsitybased heterogenous feature selection, the representation of the intrinsic latent structure embedded in multimedia, and the related hashing index  ...  These data are usually of high dimensionality, high order, and large scale. Moreover, different types of media data are interrelated everywhere in a complicated and extensive way by context prior.  ...  Lasso and nonnegative garotte In statistical community, lasso [71] is a shrinkage and variable selection method for linear regression, which is a penalized least square method imposing an 1 -norm penalty  ... 
doi:10.1007/s13735-012-0001-9 fatcat:4ihorofn6zbg3mzqnifihgcydm

Nonnegative Restricted Boltzmann Machines for Parts-based Representations Discovery and Predictive Model Stabilization [article]

Tu Dinh Nguyen, Truyen Tran, Dinh Phung, Svetha Venkatesh
2017 arXiv   pre-print
We enhance such capacity of RBMs by introducing nonnegativity into the model weights, resulting in a variant called nonnegative restricted Boltzmann machine (NRBM).  ...  We demonstrate the capacity of our model on applications such as handwritten digit recognition, face recognition, document classification and patient readmission prognosis.  ...  Section 3 presents the derivation and properties of our nonnegative RBM, followed by its applications in linear predictive model stabilization in Section 4.  ... 
arXiv:1708.05603v1 fatcat:pss7kaqzibg43of2w63dhtuwem

A dual Newton based preconditioned proximal point algorithm for exclusive lasso models [article]

Meixia Lin, Defeng Sun, Kim-Chuan Toh, Yancheng Yuan
2019 arXiv   pre-print
In addition, we derive the corresponding HS-Jacobian to the proximal mapping and analyze its structure --- which plays an essential role in the efficient computation of the PPA subproblem via applying  ...  In this paper, we propose a highly efficient dual Newton based preconditioned proximal point algorithm (PPDNA) to solve machine learning models involving the exclusive lasso regularizer.  ...  Application: index exchange-traded fund (index ETF) In this subsection, we apply the exclusive lasso model in a real application in finance.  ... 
arXiv:1902.00151v2 fatcat:smfjh3xojfbnfhjlicodu7c4cq

Smooth Adjustment for Correlated Effects [article]

Yuehan Yang, Hu Yang
2019 arXiv   pre-print
We show by simulations and applications that the proposed methods often outperforms other methods.  ...  A variety of methods have been developed in recent years, yet it is still challenging to keep accurate estimation when there are complex correlation structures among predictors and the response.  ...  First, a brief introduction of index tracking is provided: One of the popular investment products in the financial market is a collective investment scheme, called index tracking, which aims to replicate  ... 
arXiv:1901.05229v1 fatcat:rbwvilh6qzfk5oegakqkzujefi

Online coordinate descent for adaptive estimation of sparse signals

Daniele Angelosante, Juan Andres Bazerque, Georgios B. Giannakis
2009 2009 IEEE/SP 15th Workshop on Statistical Signal Processing  
In addition to computational savings offered when processing time-invariant sparse parameter vectors, both schemes can be used for tracking slowly varying sparse signals.  ...  Analysis and preliminary simulations confirm that when the true signal is sparse the proposed estimators converge to a time-weighted least-absolute shrinkage and selection operator, and both outperform  ...  in various applications; see e.g., [1, 2] .  ... 
doi:10.1109/ssp.2009.5278561 fatcat:ftwzajc3r5e53hmmrenypwxzy4

Sparse nonnegative interaction models

Mirai Takayanagi, Yasuo Tabei, Einoshin Suzuki, Hiroto Saigo
2021 IEEE Access  
INDEX TERMS LASSO/LARS, itemset mining, nonnegative least squares, variable interaction, interpretable machine learning VOLUME 4, 2016  ...  The algorithm proceeds in an iterative fashion, such that an optimal interaction term is searched by a branch-and-bound subroutine, and added to the solution set one another.  ...  ACKNOWLEDGMENT This work was supported by JSPS KAKENHI Grant Numbers 19H04176 and 21H01684.  ... 
doi:10.1109/access.2021.3099473 fatcat:s2fusyjzozgjlni7qncwyofnim

Informative Sensor and Feature Selection via Hierarchical Nonnegative Garrote

Kamran Paynabar, Judy Jin, Matthew P. Reed
2015 Technometrics  
Placing sensors in every station of a process or every element of a system to monitor its state or performance is usually too expensive or physically impossible.  ...  Performance of the proposed method is evaluated and compared with other existing methods through Monte-Carlo simulation.  ...  Yuan, M. (2007) Nonnegative garrote component selection in functional ANOVA models. In Proceedings of AI and Statistics, AISTATS, 656-662. 26.  ... 
doi:10.1080/00401706.2014.947383 fatcat:ggfva6rytfgh5mdxncklkiuf7a

Estimating fiber orientation distribution from diffusion MRI with spherical needlets

Hao Yan, Owen Carmichael, Debashis Paul, Jie Peng
2018 Medical Image Analysis  
As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report.  ...  In this paper, we focus on one particular representation for single q-shell data: the FOD.  ...  Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense  ... 
doi:10.1016/j.media.2018.01.003 pmid:29502033 pmcid:PMC5910185 fatcat:qpe6yvzudnb7jekyahde2sz5yq

Group sparse representation for image categorization and semantic video retrieval

YaNan Liu, Fei Wu, YueTing Zhuang
2011 Science China Information Sciences  
Introduction The classification of images and video clips based on their semantics has become increasingly popular due to its wide applications in image annotation, video retrieval, etc.  ...  It would be interesting to formulate this stage as the lasso or nonnegative garrote, because the resulting estimate of β retains sparsity. We will pursue these issues in the future work.  ... 
doi:10.1007/s11432-011-4344-2 fatcat:rx7vdz76fnbkvmzpxpj67vuata

Sparse Laplacian Shrinkage with the Graphical Lasso Estimator for Regression Problems [article]

Yuehan Yang, Siwei Xia, Hu Yang
2019 arXiv   pre-print
We also apply this method to a financial problem and prove that the proposed procedure is successful in assets selection.  ...  We propose a graph-constrained regularization procedure, named Sparse Laplacian Shrinkage with the Graphical Lasso Estimator (SLS-GLE).  ...  Figure 5 : 5 The performance of selecting 70 stocks in index tracking. The first row shows the predicted ATE of SLS-GLE. The second row shows the forecasting index tracking result.  ... 
arXiv:1904.04664v1 fatcat:rajjnxfejbdzdcv3ja543wfg6i

SWAGGER: Sparsity Within and Across Groups for General Estimation and Recovery [article]

Charles Saunders, Vivek K Goyal
2020 arXiv   pre-print
Proposed in this work is a nonconvex structured sparsity penalty that promotes one-sparsity within arbitrary overlapping groups in a vector.  ...  We show multiple example use cases (including a total variation variant), demonstrate synergy between it and other regularizers, and propose an algorithm to efficiently solve problems regularized or constrained  ...  Ma for comments on the manuscript, and S. W. Seidel, J. Rapp, J. Murray-Bruce and I. Selesnick for discussions.  ... 
arXiv:2006.01714v3 fatcat:jlnzepz3irf5rdazco6vi3nlt4

Distributed Sparse Linear Regression

Gonzalo Mateos, Juan Andrés Bazerque, Georgios B. Giannakis
2010 IEEE Transactions on Signal Processing  
The ideas in this paper can be easily extended for the purpose of fitting related models in a distributed fashion, including the adaptive Lasso, elastic net, fused Lasso and nonnegative garrote.  ...  A motivating application is explored in the context of wireless communications, whereby sensing cognitive radios collaborate to estimate the radio-frequency power spectrum density.  ...  In summary, the DQP-Lasso entails a global outer iteration to attain consensus (in the index ), and also local inner iterations ran at every agent to minimize (8) and update for all .  ... 
doi:10.1109/tsp.2010.2055862 fatcat:uu5jkwywungcpj73gf3ltmrhb4
« Previous Showing results 1 — 15 out of 638 results