搜索结果: 1-15 共查到“数学 Regularization”相关记录33条 . 查询时间(0.049 秒)
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Convergence and Implicit Regularization of Deep Learning Optimizers
深度学习 优化 收敛 隐式正则化
font style='font-size:12px;'>
2023/4/13
In this talk, I will present our recent work on the convergence/generalization analysis for the popular optimizers in deep learning. (1) We establish the convergence for Adam under (L0,L1 ) smoothness...
Regularization methods for high-dimensional instrumental variables regression with an application to genetical genomics
Causal inference Confounding Endogeneity Sparse regression
font style='font-size:12px;'>
2016/1/25
In genetical genomics studies, it is important to jointly analyze gene expression data and genetic variants in exploring their associations with complex traits, where the dimensionality of gene expres...
Regularization methods for high-dimensional instrumental variables regression with an application to genetical genomics
Causal inference Confounding Endogeneity Sparse regression
font style='font-size:12px;'>
2016/1/20
In genetical genomics studies, it is important to jointly analyze gene expression data and genetic variants in exploring their associations with complex traits, where the dimensionality of gene expres...
Regularization and variable selection via the elastic net
Grouping effect LARS algorithm Lasso Penalization p>n problem Variable selection
font style='font-size:12px;'>
2015/8/21
We propose the elastic net, a new regularization and variable selection method. Real world data and a simulation study show that the elastic net often outperforms the lasso, while enjoying a similar s...
Efficient Quadratic Regularization for Expression Arrays
quadratic regularization euclidean methods SVD eigengenes
font style='font-size:12px;'>
2015/8/21
Gene expression arrays typically have 50 to 100 samples and 1,000 to 20,000 variables (genes).There have been many attempts to adapt statistical models for regression and classification to these data,...
The Entire Regularization Path for the Support Vector Machine
Entire Regularization Path Support Vector Machine
font style='font-size:12px;'>
2015/8/21
In this paper we argue that the choice of the SVM cost parameter can be critical. We then derive an algorithm that can fit the entire path of SVM solutions for every value of the cost parameter, with ...
L1-regularization path algorithm for generalized linear models
Generalized linear model Lasso Path algorithm Predictor–corrector method Regularization Variable selection
font style='font-size:12px;'>
2015/8/21
We introduce a path following algorithm for L1-regularized generalized linear models. The L 1-regularization procedure is useful especially because it, in effect, selects variables according to the am...
BOOSTING ALGORITHMS:REGULARIZATION,PREDICTION AND MODEL FITTING
Generalized linear models Generalized additive models Gradient boosting Survival analysis Variable selection Software
font style='font-size:12px;'>
2015/8/21
We present a statistical perspective on boosting. Special emphasis is given to estimating potentially complex parametric or nonparametric models, including generalized linear and additive models as we...
Comment:Boosting Algorithms:Regularization,Prediction and Model Fitting
Boosting Algorithms Regularization Prediction Model Fitting
font style='font-size:12px;'>
2015/8/21
We congratulate the authors (hereafter BH) for an interesting take on the boosting technology, and for developing a modular computational environment in R for exploring their models. Their use of low-...
Spectral Regularization Algorithms for Learning Large Incomplete Matrices
collaborative filtering nuclear norm spectral regularization netflix prize large scale convex optimization
font style='font-size:12px;'>
2015/8/21
We use convex relaxation techniques to provide a sequence of regularized low-rank solutions for large-scale matrix completion problems. Using the nuclear norm as a regularizer, we provide a simple and...
Regularization Paths for Cox’s Proportional Hazards Model via Coordinate Descent
survival Cox model lasso elastic net
font style='font-size:12px;'>
2015/8/21
We introduce a pathwise algorithm for the Cox proportional hazards model, regularized by convex combinations of `1 and `2 penalties (elastic net). Our algorithm fits via cyclical coordinate descent, a...
Dynamic emission tomography - regularization and inversion
Emission tomography subtracting the poison radon pathology emission source static pathological inverse
font style='font-size:12px;'>
2015/8/11
The problem of emission tomography, inverting the attenuated Radon transform, is moderately ill-posed if the unknown emission source is static. Here we consider the case where the emission source is d...
Segmentation of ARX-models using sum-of-norms regularization
Segmentation Regularization ARX-models
font style='font-size:12px;'>
2015/8/7
Segmentation of time-varying systems and signals into models whose parameters are piecewise constant in time is an important and well studied problem. It is here formulated as a least-squares problem ...
Escape, collisions and regularization in the variational approach to the N-body problem
Escape collisions regularization variational approach N-body problem
font style='font-size:12px;'>
2015/3/18
Escape, collisions and regularization in the variational approach to the N-body problem.
A two-way regularization method for MEG source reconstruction
Inverse problem MEG two-way regularization spatiotemporal
font style='font-size:12px;'>
2012/11/23
The MEG inverse problem refers to the reconstruction of the neural activity of the brain from magnetoencephalography (MEG) measurements. We propose a two-way regularization (TWR) method to solve the M...