genlasso - Path Algorithm for Generalized Lasso Problems

Computes the solution path for generalized lasso problems. Important use cases are the fused lasso over an arbitrary graph, and trend fitting of any given polynomial order. Specialized implementations for the latter two subproblems are given to improve stability and speed. See Taylor Arnold and Ryan Tibshirani (2016) <doi:10.1080/10618600.2015.1008638>.

Last updated

7.76 score 35 stars 5 dependents 219 scripts 881 downloads

dspline - Tools for Computations with Discrete Splines

Discrete splines are a class of univariate piecewise polynomial functions which are analogous to splines, but whose smoothness is defined via divided differences rather than derivatives. Tools for efficient computations relating to discrete splines are provided here. These tools include discrete differentiation and integration, various matrix computations with discrete derivative or discrete spline bases matrices, and interpolation within discrete spline spaces. These techniques are described in Tibshirani (2020) <doi:10.48550/arXiv.2003.03886>.

Last updated

cpp

5.92 score 7 stars 1 dependents 6 scripts 601 downloads

quantgen - Tools for generalized quantile modeling

Tools for generalized quantile modeling: regularized quantile regression (with generalized lasso penalties and noncrossing constraints), cross-validation, quantile extrapolation, and quantile ensembles.

Last updated

5.36 score 1 dependents 36 scripts

tvdenoising - Univariate Total Variation Denoising

Total variation denoising can be used to approximate a given sequence of noisy observations by a piecewise constant sequence, with adaptively-chosen break points. An efficient linear-time algorithm for total variation denoising is provided here, based on Johnson (2013) <doi:10.1080/10618600.2012.681238>.

Last updated

cpp

3.65 score 1 stars 1 dependents 2 scripts 217 downloads

conformalInference.multi - Conformal Inference Tools for Regression with Multivariate Response

It computes full conformal, split conformal and multi-split conformal prediction regions when the response variable is multivariate (i.e. dimension is greater than one). Moreover, the package also contains plot functions to visualize the output of the full and split conformal functions. To guarantee consistency, the package structure mimics the univariate package 'conformalInference' by Ryan Tibshirani. See Lei, G’sell, Rinaldo, Tibshirani, & Wasserman (2018) <doi:10.1080/01621459.2017.1307116> for full and split conformal prediction in regression, and Barber, Candès, Ramdas, & Tibshirani (2023) <doi:10.1214/23-AOS2276> for extensions beyond exchangeability.

Last updated

1.93 score 17 scripts 565 downloads

conformalInference.fd - Tools for Conformal Inference for Regression in Multivariate Functional Setting

It computes full conformal, split conformal and multi split conformal prediction regions when the response has functional nature. Moreover, the package also contain a plot function to visualize the output of the split conformal. To guarantee consistency, the package structure mimics the univariate 'conformalInference' package of professor Ryan Tibshirani. The main references for the code are: Diquigiovanni, Fontana, and Vantini (2021) <arXiv:2102.06746>, Diquigiovanni, Fontana, and Vantini (2021) <arXiv:2106.01792>, Solari, and Djordjilovic (2021) <arXiv:2103.00627>.

Last updated

1.41 score 26 scripts 205 downloads