The elements of statistical learning: data mining, inference and prediction

By James Franklin. 2005

4,748 citations recorded by the source corpus.

Subfields: Information Systems, Statistics and Probability, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Statistics and Probability

In Statistical Learning Theory

Citations in the corpus

Causal Regularization (2019, background): “where λ is a regularization parameter (Hastie et al., 2001).”
Machine Learning that Matters (2012, methodology): “ that the performance obtained by training a model M on data set X may not reﬂect M’s performance on other data sets drawn from the same problem, i.e., training loss is an underestimate of test loss (Hastie et al., 2001). Strategies such as splitting X into training and test sets or cross-validation”
BART: Bayesian Additive Regression Trees (2008, methodology): “implemented as gbm by Ridgeway (2004), random forests (Breiman 2001), MARS”
CAM: Causal Additive Models, high-dimensional order search and penalized regression (2013, methodology): “major challenges with respect to computation and statistical accuracy. Our approach is generic, taking advantage of the tools 1 arXiv:1310.1533v1 [stat.ME] 6 Oct 2013 in sparse regression techniques (Hastie et al., 2009; Buhlmann and van de Geer, 2011, cf.) which have been successively established i”
A Proximal Stochastic Gradient Method with Progressive Variance Reduction (2014, background): “4; and Baidu Inc., Beijing 100085. Email: tzhang@stat.rutgers.edu. 1 Problems of this form often arise in machine learning and statistics, known as regularized empirical risk minimization; see, e.g., [HTF09]. In such problems, we are given a collection of training examples (a 1,b 1),...,(an,bn), whe”
TPOT: A Tree-based Pipeline Optimization Tool for Automating Machine Learning (2016, methodology): “All implementations of the machine learning algorithms listed below are from scikit-learn (except XGBoost), and we refer to the scikit-learn documentation [16] and [9] for detailed explanations of the machine learning algorithms used in TPOT.”
A data-driven approach to predict the success of bank telemarketing (2014, methodology): “The probabilistic SVM output is given by [35]: f ( x i ) = mj =1 y j α j K ( x j , x i ) + b and , where m is the number of support vectors, Before ﬁtting the NN and SVM models, the input data is ﬁrst standardized to a zero mean and one standard deviation [13].”
Deep learning for computational biology (2016, neutral): “If the data set is small, k-fold cross-validation or bootstrapping can be used instead (Hastie et al , 2005).”