Talks & Notes
Talks
CVXPY Workshop
Development Plans for CVXR Stanford University, Stanford, CA. | February 19, 2026
CVXR is the R port of CVXPY and has a developer community of two. As a result, it has fallen behind CVXPY in features but new AI development tools plus facilities in R offer hope of catching up. In this talk we describe our plans and present data from some early experiments that sound promising. The talk will be quite interactive and we welcome feedback from seasoned CVXPY community.
WU Vienna Research Seminar 2024
Elastic Net Regularization for GLMs and Extensions Vienna, Austria (Zoom) | January 24, 2024
The R package ‘glmnet’ is widely used for fitting lasso and elastic net models and has undergone continuous development over the years. Some recent updates allow for fitting elastic net regularized regression to all generalized linear model families, Cox models to start-stop data, and fitting relaxed lasso models. I will discuss the design and implementation of these features together with some related examples. This is joint work with Kenneth Tay and Trevor Hastie.
WU Vienna Research Seminar 2021
Easy to Use Programs for Bootstrap Confidence Intervals Vienna, Austria (online) | April 14, 2021
The “standard intervals” for a parameter theta of interest, thetahat +- 1.96*sigmahat (for approximate 95% coverage) are a mainstay of applied statistical practice, and can be computed in an almost automatic fashion in a wide range of situations. They are immensely useful but sometimes not very accurate. Bootstrap confidence intervals require much more computation, but improve coverage accuracy by an order of magnitude. Modern computational capabilities make bootstrap intervals practical on a routine basis. This talk concerns bcaboot, a new package of R programs, that aim to produce bootstrap confidence automatically, without requiring special calculations from the statistician. Joint talk with Brad Efron. Host: Kurt Hornik.
IPAM 2018 Workshop
Algorithmic Challenges in Protecting Privacy for Biomedical Data Los Angeles, USA | January 8, 2018
The R programming environment provides a rich suite of methods and algorithms for statistical model fitting and computation in general. The exploratory interface of R makes it an ideal platform for prototyping, analyzing and deploying new algorithms in an open and extensible manner. This tutorial will begin with a short self-contained introduction to R and its package mechanism for programming extensions. We will then discuss some packages for distributed, cryptographic, homomorphic, and differential privacy computations. The tutorial will include hands-on programming exercises. The goal is to provide the background and programming knowledge so that participants can develop their own packages implementing new algorithms.
Notes
Quantifying R’s Impact
A document examining the impact of the R Project on statistical computing and data science. Comments welcome.
Posts
