Filters








176,481 Hits in 4.2 sec

Fused inverse regression with multi-dimensional responses

Youyoung Cho, Hyoseon Hana, Jae Keun Yoo
2021 Communications for Statistical Applications and Methods  
Sufficient dimension reduction provides effective tools for the reduction, but there are few sufficient dimension reduction methodologies for multivariate regression.  ...  The proposed approaches are robust to the numbers of clusters or slices and improve the estimation results over existing methods by fusing many kernel matrices.  ...  In regression of Y ∈ R u |X ∈ R p , sufficient dimension reduction (SDR) seeks to replace the original p-dimensional predictors X by its lower-dimensional predictor η T X without loss of information on  ... 
doi:10.29220/csam.2021.28.3.267 fatcat:taf6ty4ln5defjjd47uwu4e4d4

Clustering Algorithm for Time Series with Similar Shapes

2018 KSII Transactions on Internet and Information Systems  
The reason for such a problem is that the existing algorithms do not consider the limitations on the size of the generated clusters, and use a dimension reduction method in which the information loss is  ...  In the clustering step, we use density-based spatial clustering of applications with noise (DBSCAN) to create a precluster.  ...  [1] used symbolic aggregate approximation (SAX) [7] as a dimension-reduction method for time series data with high-dimensional characteristics.  ... 
doi:10.3837/tiis.2018.07.008 fatcat:i4xhadnfdvaolha2unqqx66nmm

On hierarchical clustering in sufficient dimension reduction

Chaeyeon Yoo, Younju Yoo, Hye Yeon Um, Jae Keun Yoo
2020 Communications for Statistical Applications and Methods  
The K-means clustering algorithm has had successful application in sufficient dimension reduction.  ...  clustering algorithm has not yet been done in a sufficient dimension reduction context.  ...  Acknowledgements For Chaeyeon Yoo,  ... 
doi:10.29220/csam.2020.27.4.431 fatcat:kanywqfyujey3ajxik7543yiqy

A minimum discrepancy approach to multivariate dimension reduction via $k$-means inverse regression

Akim Adekpedjou, C. Messan Setodji, Xuerong Meggie Wen
2009 Statistics and its Interface  
We proposed a new method to estimate the intra-cluster adjusted central subspace for regressions with multivariate responses.  ...  Our method was designed to recover the intracluster information and outperformed previous method with respect to estimation accuracies on both the central subspace and its dimension.  ...  sufficient predictors from the four marginal dimension reduction models.  ... 
doi:10.4310/sii.2009.v2.n4.a11 fatcat:ekgytmy3sfbw7o6v2w6dbyn64e

Comparing K-Value Estimation for Categorical and Numeric Data Clustring

K. Arunprabha, V. Bhuvaneswari
2010 International Journal of Computer Applications  
The Gmeans algorithm is based on a statistical test for the hypothesis that a subset of data follows a Gaussian distribution.  ...  We used an improved algorithm for learning k while clustering the Categorical clustering. A Clustering algorithm Gaussian means applied in k-means paradigm that works well for categorical features.  ...  Both these tests are one dimensional test. We have a high dimensional dataset; we reduce the dimensions using dimension reduction method, so we learning true dimension under PCA method.  ... 
doi:10.5120/1565-1875 fatcat:zsuibcmoebafpcrttnhkvgcdz4

Page 3241 of Mathematical Reviews Vol. , Issue 2004d [page]

2004 Mathematical Reviews  
Amir (IL-HEBR-CSE; Jerusalem) ; Tishby, Naftali (IL-HEBR-INC; Jerusalem) Sufficient dimensionality reduction.  ...  In this paper we introduce an information theoretic nonlinear method for finding a most informative such dimension reduction.  ... 

Nonlinear Signal Sources Estimation Based on Nonlinear Dimension Reduction

Hong-yi LI, Zhi-xuan MA, Di ZHAO
2018 DEStech Transactions on Engineering and Technology Research  
In this paper, we propose an estimation method by combining the ICA and nonlinear dimension reduction.  ...  Our experimental results show that the proposed algorithm outperforms methods for comparison under nonlinear condition.  ...  Dimensionality reduction aims to transform high-dimensional data to a low-dimensional feature space.  ... 
doi:10.12783/dtetr/apop2017/18734 fatcat:mx3y6zqhpras5oewkpc2eadi7u

Sufficient Component Analysis for Supervised Dimension Reduction [article]

Makoto Yamada, Gang Niu, Jun Takagi, Masashi Sugiyama
2011 arXiv   pre-print
The purpose of sufficient dimension reduction (SDR) is to find the low-dimensional subspace of input features that is sufficient for predicting output values.  ...  Through large-scale experiments on real-world image classification and audio tagging problems, the proposed method is shown to compare favorably with existing dimension reduction approaches.  ...  Kenji Fukumizu for providing us the KDR code and Prof. Taiji Suzuki for his valuable comments. MY was supported by the JST PRESTO program. GN was supported by the MEXT scholarship.  ... 
arXiv:1103.4998v1 fatcat:dwgj5szbzncxxlvwkv5wgtgkoe

Comparisons of Non-Gaussian Statistical Models in DNA Methylation Analysis

Zhanyu Ma, Andrew Teschendorff, Hong Yu, Jalil Taghia, Jun Guo
2014 International Journal of Molecular Sciences  
Comparisons and analysis of different dimension reduction strategies and unsupervised clustering methods are presented.  ...  Afterwards, non-Gaussian statistical model-based unsupervised clustering strategies are applied to cluster the data.  ...  Acknowledgments The authors would like to thank the editor for organizing the review process and thank the anonymous reviewers for their efforts in reviewing this manuscript and providing fruitful suggestions  ... 
doi:10.3390/ijms150610835 pmid:24937687 pmcid:PMC4100184 fatcat:mjukdxenc5an7a37uzruntfjs4

Speaker diarization of broadcast streams using two-stage clustering based on i-vectors and cosine distance scoring

Jan Silovsky, Jan Prazak
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper we present our system for speaker diarization of broadcast news based on recent advances in the speaker recognition field.  ...  Finally, two-stage clustering employing BIC-based clustering to pre-cluster segments in the first stage is examined and showed to yield further performance improvement.  ...  Fig. 4(a) shows the effect of different LDA dimension reductions for systems operating with total variability spaces of dimensions of 300 and 400.  ... 
doi:10.1109/icassp.2012.6288843 dblp:conf/icassp/SilovskyP12 fatcat:vmj2pkrlw5fj7jxbzsu5qie6cq

Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach Using MAESTRO [article]

Hyoukjun Kwon, Prasanth Chatarasi, Michael Pellauer, Angshuman Parashar, Vivek Sarkar, Tushar Krishna
2020 arXiv   pre-print
execution time and energy efficiency for a DNN model and hardware configuration.  ...  We codify this analysis into an analytical cost model, MAESTRO (Modeling Accelerator Efficiency via Spatio-Temporal Reuse and Occupancy), that estimates various cost-benefit tradeoffs of a dataflow including  ...  ACKNOWLEDGEMENT We thank Joel Emer for insightful advice and constructive comments to improve this work; Vivienne Sze and Yu-Hsin Chen for their insights and taxonomy that motivated this work.  ... 
arXiv:1805.02566v6 fatcat:3656k7gkcbfbxewgcebz7v2wrq

Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates [article]

Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek, Volker Roth
2020 arXiv   pre-print
Based on the sufficiently reduced covariate, we transfer the relevant information to cases where data is missing at test time, allowing us to reliably and accurately estimate the effects of an intervention  ...  Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding.  ...  Overall, we we can perform a sufficient reduction of the high-dimensional covariate information to between 4 and 6 dimensions, while accurately estimating Y .  ... 
arXiv:1807.02326v3 fatcat:o64pbwr4kbenlbpb3f5xtfrnhq

Evaluating Dimensionality Reduction Techniques For Visual Category Recognition Using Rényi Entropy

Richard Bowden, Ashish Gupta
2011 Zenodo  
The value of the lower dimension is based on estimation of intrinsic dimensionality using three methods for all categories.  ...  INTRINSIC DIMENSIONALITY ESTIMATION The choice of dimension of the lower dimensional sub-space is based on the intrinsic dimensionality of the visual category.  ... 
doi:10.5281/zenodo.42618 fatcat:leygi75v2jgqvkv723uikhrd4e

Poisson factor models with applications to non-normalized microRNA profiling

Seonjoo Lee, Pauline E. Chugh, Haipeng Shen, R. Eberle, Dirk P. Dittmer
2013 Computer applications in the biosciences : CABIOS  
The method is shown to outperform several other normalization and dimension reduction methods in a simulation study.  ...  We develop an efficient algorithm for estimating the Poisson factor model, entitled Poisson Singular Value Decomposition with Offset (PSVDOS).  ...  See, among others, Anders and Huber (2010) and Robinson and Oshlack (2010) in the context of supervised clustering.  ... 
doi:10.1093/bioinformatics/btt091 pmid:23428639 pmcid:PMC3634185 fatcat:omt3povndbgfhgvrkh5w7okf6y

On Local Intrinsic Dimension Estimation and Its Applications

K.M. Carter, R. Raich, A.O. Hero
2010 IEEE Transactions on Signal Processing  
There has been much work done on estimating the global dimension of a data set, typically for the purposes of dimensionality reduction.  ...  In this paper, we present multiple novel applications for local intrinsic dimension estimation.  ...  Finn and the Department of Pathology, University of Michigan, for the cytometry data and diagnoses. They thank the reviewers of this paper for their significant contributions.  ... 
doi:10.1109/tsp.2009.2031722 fatcat:t7bfczytszcohivvjsvwjrwhny
« Previous Showing results 1 — 15 out of 176,481 results