公开(公告)号：US09684538B1

公开(公告)日：2017-06-20

申请号：US15341263

申请日：2016-11-02

Applicant: SAS Institute Inc.

Inventor： Jun Liu ,  Ruiwen Zhang ,  Yan Xu ,  Joshua Griffin

IPC: G06F7/32 ,  G06F9/48 ,  G06F9/50 ,  G06N99/00 ,  G06F17/16 ,  G06F17/17

CPC classification number: G06F17/16

Abstract: A power method can be enhanced. For example, an electronic communication indicating a job to be performed can be received. A best rank-1 approximation of a matrix associated with the job can be determined using the power method. Each iteration of the power method can include determining a point that lies on a line passing through (i) a first value for a first singular vector from an immediately prior iteration of the power method; and (ii) a second value for the first singular vector from another prior iteration of the power method. Each iteration of the power method can also include determining, by performing the power method using the point, a current value for the first singular vector and a current value for a second singular vector for a current iteration of the power method. The job can then be performed using the best rank-1 approximation of the matrix.

公开(公告)号：US10303818B2

公开(公告)日：2019-05-28

申请号：US15237209

申请日：2016-08-15

Applicant: SAS Institute Inc.

Inventor： Jun Liu ,  Ruiwen Zhang ,  Zheng Zhao

IPC: G06N20/00 ,  G06F17/11 ,  G06F17/50

Abstract: Processing speeds for generating a model can be enhanced. For example, the model can be generated by using regression coefficient values as weights for independent variables in the model. The regression coefficient values can be determined using a coordinate descent method to find a minimum value of a least absolute shrinkage and selection operator cost function. Each iteration of the coordinate descent method can include determining a starting coordinate based on (i) a previous starting coordinate or a previous regression coefficient value from an immediately prior iteration of the coordinate descent method; (ii) a current regression coefficient value associated with a current iteration of the coordinate descent method; and (iii) a refinement factor configured to minimize a result of a univariate algorithm. Each iteration can also include performing a coordinate descent using the starting coordinate to determine a next regression coefficient value for a next iteration of the coordinate descent method.

公开(公告)号：US10049302B1

公开(公告)日：2018-08-14

申请号：US15911882

申请日：2018-03-05

Applicant: SAS Institute Inc.

Inventor： Jun Liu ,  Yan Xu ,  Joshua David Griffin ,  Manoj Keshavmurthi Chari

IPC: G06K9/62 ,  G06F17/30 ,  G06F15/18 ,  G06N7/00 ,  G06F17/16 ,  G06F17/18

Abstract: A computing device trains models for streaming classification. A baseline penalty value is computed that is inversely proportional to a square of a maximum explanatory variable value. A set of penalty values is computed based on the baseline penalty value. For each penalty value of the set of penalty values, a classification type model is trained using the respective penalty value and the observation vectors to compute parameters that define a trained model, the classification type model is validated using the respective penalty value and the observation vectors to compute a validation criterion value that quantifies a validation error, and the validation criterion value, the respective penalty value, and the parameters that define a trained model are stored to the computer-readable medium. The classification type model is trained to predict the response variable value of each observation vector based on the respective explanatory variable value of each observation vector.

公开(公告)号：US20160247089A1

公开(公告)日：2016-08-25

申请号：US14834365

申请日：2015-08-24

Applicant: SAS Institute Inc.

Inventor： Zheng Zhao ,  Jun Liu ,  James Allen Cox

IPC: G06N99/00

CPC classification number: G06N99/005

Abstract: A system for machine training can comprise one or more data processors and a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform operations including: accessing a dataset comprising data tracking a plurality of features; determining a series of values for a regularization parameter of a sparse support vector machine model, the series including an initial regularization value and a next regularization value; computing an initial solution to the sparse support vector machine model for the initial regularization value; identifying, using the initial solution, inactive features of the sparse support vector machine model for the next regularization value; and computing a next solution to the sparse support vector machine model for the next regularization value, wherein computing the next solution includes excluding the inactive features.

Abstract translation: 用于机器训练的系统可以包括一个或多个数据处理器和包含指令的非暂时计算机可读存储介质，所述指令在所述一个或多个数据处理器上执行时使所述一个或多个数据处理器执行操作，所述操作包括：访问 数据集，其包括跟踪多个特征的数据; 确定稀疏支持向量机模型的正则化参数的一系列值，该系列包括初始正则化值和下一个正则化值; 计算初始正则化值的稀疏支持向量机模型的初始解; 使用初始解决方案识别用于下一个正则化值的稀疏支持向量机模型的非活动特征; 并计算下一个正则化值的稀疏支持向量机模型的下一个解决方案，其中计算下一个解决方案包括排除非活动特征。

公开(公告)号：US09495647B2

公开(公告)日：2016-11-15

申请号：US14834365

申请日：2015-08-24

Applicant: SAS Institute Inc.

Inventor： Zheng Zhao ,  Jun Liu ,  James Allen Cox

IPC: G06F15/18 ,  G06N99/00

CPC classification number: G06N99/005

Abstract: A system for machine training can comprise one or more data processors and a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform operations including: accessing a dataset comprising data tracking a plurality of features; determining a series of values for a regularization parameter of a sparse support vector machine model, the series including an initial regularization value and a next regularization value; computing an initial solution to the sparse support vector machine model for the initial regularization value; identifying, using the initial solution, inactive features of the sparse support vector machine model for the next regularization value; and computing a next solution to the sparse support vector machine model for the next regularization value, wherein computing the next solution includes excluding the inactive features.

Abstract translation: 用于机器训练的系统可以包括一个或多个数据处理器和包含指令的非暂时计算机可读存储介质，所述指令在所述一个或多个数据处理器上执行时使所述一个或多个数据处理器执行操作，所述操作包括：访问 数据集，其包括跟踪多个特征的数据; 确定稀疏支持向量机模型的正则化参数的一系列值，该系列包括初始正则化值和下一个正则化值; 计算初始正则化值的稀疏支持向量机模型的初始解; 使用初始解决方案识别用于下一个正则化值的稀疏支持向量机模型的非活动特征; 并计算下一个正则化值的稀疏支持向量机模型的下一个解决方案，其中计算下一个解决方案包括排除非活动特征。

公开(公告)号：US20150324324A1

公开(公告)日：2015-11-12

申请号：US14571224

申请日：2014-12-15

Applicant: SAS Institute Inc.

Inventor： Jun Liu ,  Zheng Zhao

IPC: G06F17/10

CPC classification number: G06F17/18 ,  G06F17/10

Abstract: Systems and methods for linear regression using safe screening techniques. A computing system may receive, from a user of the system, a data set including a set of variables, the set of variables being related to a linear model for predicting a response variable of the data set. The computing system may determine an active set of variables using a safe screening algorithm The computing system may generate the linear model using the active set and a least angle regression algorithm. The computing system may provide, to the user of the system, information related to the linear model.

Abstract translation: 使用安全筛选技术进行线性回归的系统和方法。 计算系统可以从系统的用户接收包括一组变量的数据集，该变量集合与用于预测数据集的响应变量的线性模型相关。 计算系统可以使用安全筛选算法确定一组有效的变量。计算系统可以使用活动集和最小角回归算法生成线性模型。 计算系统可以向系统的用户提供与线性模型相关的信息。