Adaptive Regression by Mixing

By Yuhong Yang. 2001

323 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/eecbb6deedb9f4b09477fd18092d5d89de3e9c42

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Aggregating regression procedures to improve performance (2004, methodology): “The result is proved in Yang (2001) for the case where there are finitely many, say J, candidate procedures with equal prior weight j ¼ 1=J for 1 < j < J : The proof for the general case can be done similarly.”
CONSISTENCY OF CROSS VALIDATION FOR COMPARING REGRESSION PROCEDURES (2007, methodology): “See Opsomer, Wang and Yang [17] for a review and references related to the use of CV for bandwidth selection for nonparametric regression with dependent errors.”
User-friendly introduction to PAC-Bayes bounds (2021, background): “Many aggregates share a formal similarity with the EWA of online learning and with the Gibbs posterior of the PAC-Bayes approach, we refer the reader to [144, 106, 202, 139, 203, 42, 206, 119, 116, 64, 40, 183, 65, 60, 63, 59, 62, 126, 61].”
Model Selection Techniques: An Overview (2018, methodology): “In practice, data analysts may need to utilize data-driven tools such as model averaging [80], resampling [81], conﬁdence set for models [82], or model selection diagnostic tools such as the parametricness index introduced in Section III in order to make sure the selected variables are stable and…”
Model selection via testing: an alternative to (penalized) maximum likelihood estimators (2006, methodology): “Related points of view about the relationships between the minimax risk and the metric structure of the parameter space are to be found in Yatracos [73], Yang and Barron [72], Devroye and Lugosi [28] and Yang [69].”
Time-varying model averaging (2020, unknown): “In recent ears, frequentist model averaging has received growing attention in econometrics and statistics (e.g., Buckland et al. 1997), Yang (2001), Hjort and Claeskens (2003), Yuan and Yang (2005), Hansen (2007, 2008), Wan et al. (2010), Liu and kui (2013), Liu (2015) and Chen et al. (2018)).”
Cross-validation for selecting a model selection procedure (2015, background): “Note also that n v /n t = 1 yields the optimal-rate model averaging in general (e.g., Yang, 2001).”
Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity (2008, background): “The idea of mixing with exponential weights has been discussed by many authors apparently since 1970-ies (see [38] for an overview of the subject).”
Applied Linear Regression (2004, methodology): “See Fraley et al. (2011) for application to weather forecasting, Hoeting et al. (1999) for a tutorial on Bayesian model averaging in general, or Yang (2001) for other approaches.”
Focused information criterion and model averaging for generalized additive partial linear models (2011, background): “…to model selection, not only provides a kind of insurance against selecting a very poor model, but can also avoid model selection instability [Yang (2001) and Leung and Barron (2006)] by weighting/smoothing estimators across several models, instead of relying entirely on a single model…”
Least squares model averaging by Mallows criterion (2010, methodology): “Yang (2001) proposed an adaptive regression using a mixing method, and Yuan and Yang (2005) suggested a model screening step in conjunction with this method.”
Frequentist Model Average Estimators (2003, methodology): “The adaptive regression by mixing of Yang (2001) splits the data set into two parts, where one part is used for estimation and the other for measuring the quality of predictions, on basis of which model weights are constructed.”
Optimal Model Assessment, Selection, and Combination (2006, methodology): “For FMA, George (1986) constructed weights through multiple shrinkage, whereas Buckland, Burnham, and Augustin (1997) suggested that w(M) is proportional to an exponentiated negative AIC or BIC value at M. Yang (2001) used a split-sample method to determine model weights in linear regression.”
Focused Information Criteria, Model Selection, and Model Averaging in a Tobit Model With a Nonzero Threshold (2012, methodology): “The latter four cases are precisely the specifications used by Yuan and Yang (2005) in their Monte Carlo study; thus for cases 5–8, we follow Yuan and Yang (2005) by generating xi2, .”
Confidence sets for model selection by F -testing (2015, background): “See, e.g., Hoeting et al. (1999); Yang (2001); Hjort and Claeskens (2003) and references therein.”
Optimal Weight Choice for Frequentist Model Average Estimators (2011, methodology): “…Burnham, and Augustin (1997), for example, proposed a frequentist model weighting method according to values of a model selection criterion; Yang (2001, 2003) developed an adaptive regression by mixing method; Yuan and Yang (2005) further built on this method by proposing a model screening…”