Filters








1,494,605 Hits in 2.6 sec

Robust Reductions [article]

Jin-Yi Cai, Lane A. Hemaspaandra, Gerd Wechsung
1999 arXiv   pre-print
Generalizing robust reductions, we note that robustly strong reductions are built from two restrictions, robust underproductivity and robust overproductivity, both of which have been separately studied  ...  We continue the study of robust reductions initiated by Gavalda and Balcazar.  ...  In this paper, we continue the investigation of robust reductions started by Gavaldà and Balcázar [7] .  ... 
arXiv:cs/9906033v1 fatcat:wvtzx5p5fveh7gypkrknsdh3xi

Robust Graph Dimensionality Reduction

Xiaofeng Zhu, Cong Lei, Hao Yu, Yonggang Li, Jiangzhang Gan, Shichao Zhang
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In this paper, we propose conducting Robust Graph Dimensionality Reduction (RGDR) by learning a transformation matrix to map original high-dimensional data into their low-dimensional intrinsic space without  ...  \ie a reverse graph embedding of original data, a transformation matrix, and a graph matrix preserving the local similarity of original data in their low-dimensional intrinsic space; and 2) employing robust  ...  Robust Dimensionality Reduction Instead of learning a fixed graph matrix in previous manifold learning methods, in this paper, we propose to employ robust estimators to adaptively learning a reverse graph  ... 
doi:10.24963/ijcai.2018/452 dblp:conf/ijcai/ZhuLYLGZ18 fatcat:aw2kxefldzdk7kmiplnngch4tm

Robust linear dimensionality reduction

Y. Koren, L. Carmel
2004 IEEE Transactions on Visualization and Computer Graphics  
In this paper we will put special emphasize on yet another important property of our methods, namely their robustness.  ...  Dimensionality reduction is used for many purposes.  ... 
doi:10.1109/tvcg.2004.17 pmid:18579973 fatcat:lp4iqvsblfbideali34feizykq

Robust inversion, dimensionality reduction, and randomized sampling

Aleksandr Aravkin, Michael P. Friedlander, Felix J. Herrmann, Tristan van Leeuwen
2012 Mathematical programming  
We survey robust methods within a statistical framework, and propose a semistochastic optimization approach that allows dimensionality reduction.  ...  The tremendous size of such problems motivates dimensionality reduction techniques based on randomly mixing experiments.  ...  We survey robust approaches from a statistical perspective, and present a robust approach based on the heavy-tailed Student's t-distribution.  ... 
doi:10.1007/s10107-012-0571-6 fatcat:wlatctgqlne47jjdt4uqeajmom

Robust SISO controller order reduction

Vahid R. Dehkordi, Benoit Boulet, Amir G. Aghdam
2009 2009 American Control Conference  
The controller ensures system robust performance and reducing its order may result in loss of robust performance.  ...  In this paper a method is proposed to reduce the order of a single-input single-output robust controller.  ...  In robust controller order reduction problem, it is also important to guarantee that closed-loop robust performance is preserved.  ... 
doi:10.1109/acc.2009.5160516 dblp:conf/amcc/DehkordiBA09 fatcat:47adqwnswbchzbhs6qscjxrx5e

MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data [article]

George Close, Thomas Hain, Stefan Goetze
2022 arXiv   pre-print
In this work, we propose MetricGAN+/- (an extension of MetricGAN+, one such metric-motivated system) which introduces an additional network - a "de-generator" which attempts to improve the robustness of  ...  We assess this performance using PESQ and STOI and also using the Composite [27] Measure, where Csig, Cbak and Covl are intrusive measures of speech signal quality, background noise reduction quality  ... 
arXiv:2203.12369v5 fatcat:3ytwwbyw3vanvcayb53rskdnhu

Fusion frames and robust dimension reduction

Ali Pezeshki, Gitta Kutyniok, Robert Calderbank
2008 2008 42nd Annual Conference on Information Sciences and Systems  
We prove that tight fusion frames consisting of equidimensional subspaces have maximum robustness with respect to erasures of one subspace, and that the optimal dimension depends on SNR.  ...  We also show that tight fusion frames consisting of equi-dimensional subspaces with equal pairwise chordal distances are most robust with respect to two and more subspace erasures, and refer to such fusion  ...  reduction.  ... 
doi:10.1109/ciss.2008.4558533 dblp:conf/ciss/PezeshkiKC08 fatcat:odbuibycejhqdlk6xkupha6xhu

Robust Noise Reduction and Echo Cancellation [chapter]

Kristian Kroschel, Martin Heckmann
2000 Personal Wireless Communications  
Furthermore new concepts for echo reduction are presented. 1.  ...  Another aspect has to be taken into account: the system has to be robust, i.e. it has to be operable in a wide range of the signal-to-noise ratio down to 0 dB or less.  ...  Kroschel, Martin Heckmann Further research will be cncentrated on the integration of the frequency selective gain control to improve the measure of echo cencellation and the spectral subtraction for noise reduction  ... 
doi:10.1007/978-0-387-35526-9_20 fatcat:2ikekdb7jrhxhkxtwoyyo3ozha

Robust inverse regression for dimension reduction

Yuexiao Dong, Zhou Yu, Liping Zhu
2015 Journal of Multivariate Analysis  
• Title: A note on robust sufficient dimension reduction. • June, 2011. ICSA 2011 Applied Statistics Symposium, New York City. Title: A note on sliced inverse regression with missing predictors  ...  Thesis Committee Chair • Yizhi Sun, Master of Statistics, graduated in Summer 2010 Title: Robust kernel inverse regression.  ... 
doi:10.1016/j.jmva.2014.10.005 fatcat:iaal6rjyojdkzg4pa3qtoqw4ra

Robust estimation of dimension reduction space

P. Čížek, W. Härdle
2006 Computational Statistics & Data Analysis  
Most dimension reduction methods based on nonparametric smoothing are highly sensitive to outliers and to data coming from heavy-tailed distributions.  ...  We show that the recently proposed methods by Xia et al. (2002) can be made robust in such a way that preserves all advantages of the original approach.  ...  dimensional data processed by means of dimension reduction methods requires estimation methodology robust to data contamination, which can arise from miscoding or heterogeneity not captured or presumed  ... 
doi:10.1016/j.csda.2005.11.001 fatcat:l5mendm5h5bynm7efst67of4vy

The Robust Clustering With Reduction Dimension

Dyah E. Herwindiati
2012 Zenodo  
This paper discusses a robust clustering process for data images with two reduction dimension approaches; i.e. the two dimensional principal component analysis (2DPCA) and principal component analysis  ...  One of the most common forms of dimensionality reduction is the principal components analysis (PCA).  ...  Two approaches of MVV robust reduction dimension are used for clustering process.  ... 
doi:10.5281/zenodo.1082267 fatcat:mv4t6umwavaixnecuzzy6r3ncq

Robust inversion via semistochastic dimensionality reduction

Aleksandr Y. Aravkin, Michael P. Friedlander, Tristan van Leeuwen
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The tremendous size of such problems motivates the use dimensionality reduction (DR) techniques based on randomly mixing experiments.  ...  The sampling approach achieves this recovery using 20% of the effort required by a direct robust approach.  ...  Dimensionality reduction (DR) is a technique where entire groups of experiments are fused into "super" experiments (e.g., "super shots" or "random source encoding", in the seismic context) with the overall  ... 
doi:10.1109/icassp.2012.6289103 dblp:conf/icassp/AravkinFL12 fatcat:obak3zohhffanp27nguhtn7djm

Robust Estimation of Dimension Reduction Space

Pavel Cizek, Wolfgang K. Härdle
2005 Social Science Research Network  
Most dimension reduction methods based on nonparametric smoothing are highly sensitive to outliers and to data coming from heavy-tailed distributions.  ...  We show that the recently proposed methods by Xia et al. (2002) can be made robust in such a way that preserves all advantages of the original approach.  ...  dimensional data processed by means of dimension reduction methods requires estimation methodology robust to data contamination, which can arise from miscoding or heterogeneity not captured or presumed  ... 
doi:10.2139/ssrn.706821 fatcat:whggx6jzurbqrjhzalhiw6keda

Robust reductions from ranking to classification

Maria-Florina Balcan, Nikhil Bansal, Alina Beygelzimer, Don Coppersmith, John Langford, Gregory B. Sorkin
2008 Machine Learning  
Ordering by the number of wins In this section, we describe the reduction and prove the main result. The reduction consists of two components.  ...  We show that there is a robust mechanism for translating any binary classifier learning algorithm into a ranking algorithm.  ... 
doi:10.1007/s10994-008-5058-6 fatcat:ktviqzd4vfbdnaxmqrm56jis4e

Introduction and Overview [chapter]

2015 Robust Methods for Data Reduction  
BACKGROUND The field of nanostructure science and technology is a broad and interdisciplinary area of worldwide research and development activity that has been growing explosively in the past few years. While an understanding of the range and nature of functionalities that can be accessed through nanostructuring is just beginning to unfold, its tremendous potential for revolutionizing the ways in which materials and products are created is already clear. It is already having a significant
more » ... cial impact, and it will very certainly have a much greater impact in the future.
doi:10.1201/b18358-2 fatcat:dc3lorqsebhi5betudy2uxarga
« Previous Showing results 1 — 15 out of 1,494,605 results