The elements of statistical learning: data mining, inference, and prediction, 2nd Edition

By Trevor J. Hastie, Robert Tibshirani, Jerome H. Friedman. 2020

1,051 citations recorded by the source corpus.

Subfields: 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 Statistics and Probability

In Statistical Learning Theory

Citations in the corpus

Privacy-Preserving Ridge Regression on Hundreds of Millions of Records (2013, methodology): “, [11]) also build models as solutions of convex optimization problems, parametrized by user data, similar to the one we considered here.”
Fairness in Criminal Justice Risk Assessments: The State of the Art (2017, methodology): “Discussions in statistics about generalization error (Hastie et al. 2009:section 7.2) can provide one set of terms whereas concerns about errors from statistical tests can provide another.”
Statistical Arbitrage in Cryptocurrency Markets (2019, positive): “The coefﬁcients can be estimated by maximum likelihood using the observations from the training set—further details are available in Hastie et al. (2008).”
Decision support from financial disclosures with deep neural networks and transfer learning (2017, background): “These models have been shown to perform well on machine learning problems with many features and few observations [41]; hence, they are especially suited to our task, where the number of predictors exceeds the number of documents.”
CAM: Causal Additive Models, high-dimensional order search and penalized regression (2013, methodology): “Our approach is generic, taking advantage of the tools in sparse regression techniques [4, 8], cf.”
Evaluating the predictive performance of empirical estimators of natural mortality rate using information on over 200 fish species (2015, methodology): “For the tests of the Approach Evaluation and the Updated Performance, we used the tenfold cross-validation technique (Hastie et al., 2009).”
A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. (2019, methodology): “ML methods include artificial neural networks, support vector machines, and random forests [2].”
Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information (2014, methodology): “Given instances of x and y, supervised machine learning attempts to induce or train a classification model f', which is an approximation of the discrimination function, ŷ1⁄4 f'(x), and maps input data to target classes (Gahegan, 2000; Hastie et al., 2009; Kovacevic et al., 2009).”
Accelerated schemes for a class of variational inequalities (2014, background): “Tomotivate our discussion, let us mention one widespread machine learning model which helps to represent massive data in a compact way [17].”
Some methods for heterogeneous treatment effect estimation in high dimensions (2017, background): “The diﬀerence between this and CART is that in CART the pairs of functions considered are of the form { I { x j − c ≥ 0 } , I { c − x j > 0 } } , and when a product with one of the included terms in chosen, it replaces the included term in the model (Hastie et al., 2009).”
Last-Level Cache Side-Channel Attacks are Practical (2015, methodology): “To group similar trace patterns, we use a hierarchical clustering algorithm [17] with the edit distance [25] between the trace patterns as the measure of similarity.”
Highly comparative time-series analysis: the empirical structure of time series and their methods (2013, methodology): “For example, clustering the operations into four groups using k-medoids clustering [6] is depicted in figure 3a, and reflects a crude but intuitive summary of the types of methods that scientists have developed to study time series.”
Statistical significance in high-dimensional linear models (2012, background): “…work has been pursued addressing prediction of a new response variable, estimation of an underlying parameter vector and variable selection, see for example the books by Hastie, Tibshirani and Friedman (2009), B¨uhlmann and van de Geer (2011) or the more speciﬁc review article by Fan and Lv (2010).”
Handbook of Functional MRI Data Analysis: Index (2011, background): “Leave-one-out cross-validation is relatively costly in terms of computation (since the classifier has to be fit for each left-out observation) but will provide an unbiased measure of test accuracy, whereas cross-validation with larger k may sometimes be biased; ten-fold cross-validation appears to b”
Novel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson's Disease (2012, methodology): “trick to transform the data into a higher dimensional space, and construct the separating hyperplane in that space [22].”