scholarly journals An Efficient Kernel Learning Algorithm for Semisupervised Regression Problems

2015 ◽  
Vol 2015 ◽  
pp. 1-9
Author(s):  
Chao Zhang ◽  
Shaogao Lv
Keyword(s):  
Iterative Procedure ◽  
Large Scale ◽  
Simulation Experiment ◽  
Learning Algorithm ◽  
Real Data ◽  
Least Square ◽  
Theoretical Support ◽  
Regression Problems ◽  
Kernel Design ◽  
Learning Schemes

Kernel selection is a central issue in kernel methods of machine learning. In this paper, we investigate the regularized learning schemes based on kernel design methods. Our ideal kernel is derived from a simple iterative procedure using large scale unlabeled data in a semisupervised framework. Compared with most of existing approaches, our algorithm avoids multioptimization in the process of learning kernels and its computation is as efficient as the standard single kernel-based algorithms. Moreover, large amounts of information associated with input space can be exploited, and thus generalization ability is improved accordingly. We provide some theoretical support for the least square cases in our settings; also these advantages are shown by a simulation experiment and a real data analysis.

Application of a Rough Set-Based Inductive Learning System

1993 ◽  
Vol 18 (2-4) ◽  
pp. 209-220
Author(s):  
Michael Hadjimichael ◽  
Anita Wasilewska
Keyword(s):  
Machine Learning ◽  
Rough Set ◽  
Presidential Election ◽  
Predictive Accuracy ◽  
Learning Algorithm ◽  
Inductive Learning ◽  
Real Data ◽  
Semantic Content ◽  
Learning System ◽  
Voter Preferences

We present here an application of Rough Set formalism to Machine Learning. The resulting Inductive Learning algorithm is described, and its application to a set of real data is examined. The data consists of a survey of voter preferences taken during the 1988 presidential election in the U.S.A. Results include an analysis of the predictive accuracy of the generated rules, and an analysis of the semantic content of the rules.

scholarly journals Constructing Large-Scale Genetic Maps Using an Evolutionary Strategy Algorithm

Genetics ◽  
2003 ◽  
Vol 165 (4) ◽  
pp. 2269-2282
Author(s):  
D Mester ◽  
Y Ronin ◽  
D Minkov ◽  
E Nevo ◽  
A Korol
Keyword(s):  
Discrete Optimization ◽  
High Performance ◽  
Large Scale ◽  
Simulated Data ◽  
Real Data ◽  
Genetic Maps ◽  
Chromosome 1 ◽  
Evolutionary Strategy ◽  
Group A ◽  
The One

Abstract This article is devoted to the problem of ordering in linkage groups with many dozens or even hundreds of markers. The ordering problem belongs to the field of discrete optimization on a set of all possible orders, amounting to n!/2 for n loci; hence it is considered an NP-hard problem. Several authors attempted to employ the methods developed in the well-known traveling salesman problem (TSP) for multilocus ordering, using the assumption that for a set of linked loci the true order will be the one that minimizes the total length of the linkage group. A novel, fast, and reliable algorithm developed for the TSP and based on evolution-strategy discrete optimization was applied in this study for multilocus ordering on the basis of pairwise recombination frequencies. The quality of derived maps under various complications (dominant vs. codominant markers, marker misclassification, negative and positive interference, and missing data) was analyzed using simulated data with ∼50-400 markers. High performance of the employed algorithm allows systematic treatment of the problem of verification of the obtained multilocus orders on the basis of computing-intensive bootstrap and/or jackknife approaches for detecting and removing questionable marker scores, thereby stabilizing the resulting maps. Parallel calculation technology can easily be adopted for further acceleration of the proposed algorithm. Real data analysis (on maize chromosome 1 with 230 markers) is provided to illustrate the proposed methodology.

scholarly journals Kernel weighted least square approach for imputing missing values of metabolomics data

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Nishith Kumar ◽  
Md. Aminul Hoque ◽  
Masahiro Sugimoto
Keyword(s):  
Missing Data ◽  
Large Scale ◽  
Missing Values ◽  
Kernel Weight ◽  
Least Square ◽  
Data Matrix ◽  
Data Imputation ◽  
Metabolomics Data ◽  
Missing Value ◽  
Missing Data Imputation

AbstractMass spectrometry is a modern and sophisticated high-throughput analytical technique that enables large-scale metabolomic analyses. It yields a high-dimensional large-scale matrix (samples × metabolites) of quantified data that often contain missing cells in the data matrix as well as outliers that originate for several reasons, including technical and biological sources. Although several missing data imputation techniques are described in the literature, all conventional existing techniques only solve the missing value problems. They do not relieve the problems of outliers. Therefore, outliers in the dataset decrease the accuracy of the imputation. We developed a new kernel weight function-based proposed missing data imputation technique that resolves the problems of missing values and outliers. We evaluated the performance of the proposed method and other conventional and recently developed missing imputation techniques using both artificially generated data and experimentally measured data analysis in both the absence and presence of different rates of outliers. Performances based on both artificial data and real metabolomics data indicate the superiority of our proposed kernel weight-based missing data imputation technique to the existing alternatives. For user convenience, an R package of the proposed kernel weight-based missing value imputation technique was developed, which is available at https://github.com/NishithPaul/tWLSA.

A Scalable Redefined Stochastic Blockmodel

2021 ◽  
Vol 15 (3) ◽  
pp. 1-28
Author(s):  
Xueyan Liu ◽  
Bo Yang ◽  
Hechang Chen ◽  
Katarzyna Musial ◽  
Hongxu Chen ◽  
...  
Keyword(s):  
Large Scale ◽  
Network Science ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Real World Data ◽  
Computational Overhead ◽  
Stochastic Blockmodel ◽  
Np Hard Problem ◽  
Large Scale Networks ◽  
The Cost

Stochastic blockmodel (SBM) is a widely used statistical network representation model, with good interpretability, expressiveness, generalization, and flexibility, which has become prevalent and important in the field of network science over the last years. However, learning an optimal SBM for a given network is an NP-hard problem. This results in significant limitations when it comes to applications of SBMs in large-scale networks, because of the significant computational overhead of existing SBM models, as well as their learning methods. Reducing the cost of SBM learning and making it scalable for handling large-scale networks, while maintaining the good theoretical properties of SBM, remains an unresolved problem. In this work, we address this challenging task from a novel perspective of model redefinition. We propose a novel redefined SBM with Poisson distribution and its block-wise learning algorithm that can efficiently analyse large-scale networks. Extensive validation conducted on both artificial and real-world data shows that our proposed method significantly outperforms the state-of-the-art methods in terms of a reasonable trade-off between accuracy and scalability. 1

scholarly journals A Compound Wind Power Forecasting Strategy Based on Clustering, Two-Stage Decomposition, Parameter Optimization, and Optimal Combination of Multiple Machine Learning Approaches

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3586 ◽  
Author(s):  
Sizhou Sun ◽  
Jingqi Fu ◽  
Ang Li
Keyword(s):  
Wind Power ◽  
Large Scale ◽  
Wind Farm ◽  
Search Algorithm ◽  
Interpolation Method ◽  
Least Square ◽  
Support Vector ◽  
Two Stage ◽  
Wind Power Forecasting ◽  
Power Forecasting

Given the large-scale exploitation and utilization of wind power, the problems caused by the high stochastic and random characteristics of wind speed make researchers develop more reliable and precise wind power forecasting (WPF) models. To obtain better predicting accuracy, this study proposes a novel compound WPF strategy by optimal integration of four base forecasting engines. In the forecasting process, density-based spatial clustering of applications with noise (DBSCAN) is firstly employed to identify meaningful information and discard the abnormal wind power data. To eliminate the adverse influence of the missing data on the forecasting accuracy, Lagrange interpolation method is developed to get the corrected values of the missing points. Then, the two-stage decomposition (TSD) method including ensemble empirical mode decomposition (EEMD) and wavelet transform (WT) is utilized to preprocess the wind power data. In the decomposition process, the empirical wind power data are disassembled into different intrinsic mode functions (IMFs) and one residual (Res) by EEMD, and the highest frequent time series IMF1 is further broken into different components by WT. After determination of the input matrix by a partial autocorrelation function (PACF) and normalization into [0, 1], these decomposed components are used as the input variables of all the base forecasting engines, including least square support vector machine (LSSVM), wavelet neural networks (WNN), extreme learning machine (ELM) and autoregressive integrated moving average (ARIMA), to make the multistep WPF. To avoid local optima and improve the forecasting performance, the parameters in LSSVM, ELM, and WNN are tuned by backtracking search algorithm (BSA). On this basis, BSA algorithm is also employed to optimize the weighted coefficients of the individual forecasting results that produced by the four base forecasting engines to generate an ensemble of the forecasts. In the end, case studies for a certain wind farm in China are carried out to assess the proposed forecasting strategy.

scholarly journals Meta-Descent for Online, Continual Prediction

2019 ◽  
Vol 33 ◽  
pp. 3943-3950
Author(s):  
Andrew Jacobsen ◽  
Matthew Schlegel ◽  
Cameron Linke ◽  
Thomas Degris ◽  
Adam White ◽  
...  
Keyword(s):  
Gradient Descent ◽  
Large Scale ◽  
Time Series Prediction ◽  
Real Data ◽  
Second Order ◽  
Stochastic Gradient Descent ◽  
Step Size ◽  
Vector Approximation ◽  
Prediction Problems ◽  
Stationary Problems

This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGrad, keep statistics about the learning process to approximate a second order update—a vector approximation of the inverse Hessian. Another family of approaches use meta-gradient descent to adapt the stepsize parameters to minimize prediction error. These metadescent strategies are promising for non-stationary problems, but have not been as extensively explored as quasi-second order methods. We first derive a general, incremental metadescent algorithm, called AdaGain, designed to be applicable to a much broader range of algorithms, including those with semi-gradient updates or even those with accelerations, such as RMSProp. We provide an empirical comparison of methods from both families. We conclude that methods from both families can perform well, but in non-stationary prediction problems the meta-descent methods exhibit advantages. Our method is particularly robust across several prediction problems, and is competitive with the state-of-the-art method on a large-scale, time-series prediction problem on real data from a mobile robot.

Detection of differentially methylated CpG sites between tumor samples with uneven tumor purities

2019 ◽  
Vol 36 (7) ◽  
pp. 2017-2024
Author(s):  
Weiwei Zhang ◽  
Ziyi Li ◽  
Nana Wei ◽  
Hua-Jun Wu ◽  
Xiaoqi Zheng
Keyword(s):  
Real Data ◽  
R Package ◽  
Differential Methylation ◽  
Least Square ◽  
Epigenetic Mechanism ◽  
Supplementary Information ◽  
Cpg Sites ◽  
Tumor Purity ◽  
Different Sources ◽  
Normal Controls

Abstract Motivation Inference of differentially methylated (DM) CpG sites between two groups of tumor samples with different geno- or pheno-types is a critical step to uncover the epigenetic mechanism of tumorigenesis, and identify biomarkers for cancer subtyping. However, as a major source of confounding factor, uneven distributions of tumor purity between two groups of tumor samples will lead to biased discovery of DM sites if not properly accounted for. Results We here propose InfiniumDM, a generalized least square model to adjust tumor purity effect for differential methylation analysis. Our method is applicable to a variety of experimental designs including with or without normal controls, different sources of normal tissue contaminations. We compared our method with conventional methods including minfi, limma and limma corrected by tumor purity using simulated datasets. Our method shows significantly better performance at different levels of differential methylation thresholds, sample sizes, mean purity deviations and so on. We also applied the proposed method to breast cancer samples from TCGA database to further evaluate its performance. Overall, both simulation and real data analyses demonstrate favorable performance over existing methods serving similar purpose. Availability and implementation InfiniumDM is a part of R package InfiniumPurify, which is freely available from GitHub (https://github.com/Xiaoqizheng/InfiniumPurify). Supplementary information Supplementary data are available at Bioinformatics online.

Fast Multipole Virtual Boundary Element - Least Square Method for Solving 2-D Elastic Problems

2011 ◽  
Vol 204-210 ◽  
pp. 2196-2201
Author(s):  
Yan Tao Jiang ◽  
Si Tian Chen ◽  
Cheng Hua Li
Keyword(s):  
Boundary Element ◽  
Large Scale ◽  
Fast Multipole Method ◽  
Main Idea ◽  
Least Square Method ◽  
Least Square ◽  
Fast Multipole ◽  
Large Scale Problems ◽  
Virtual Boundary ◽  
Virtual Boundary Element

In this paper, the fast multipole virtual boundary element - least square method (Fast Multipole VBE - LSM) is proposed and used to simulate 2-D elastic problems, which is based on the fast multipole method (FMM) and virtual boundary element - least square method (VBE - LSM).The main idea of the method is to change computational model by applying the FMM to conventional VBE - LSM. The memory and operations could be reduced to be of linear proportion to the degree of freedom (DOF) and large scale problems could be effectively solved on a common desktop with this method. Numerical results show that this method holds virtues of high feasibility, accuracy and efficiency. Moreover, the idea of this method can be generalized and extended in application.

Sign in / Sign up

Export Citation Format

Share Document