Excerpts and takeaways from what our team is reading to inspire and inform what we build
Model-X knockoffs | April 6, 2021
A discussion on Model-X knockoffs, part of a family of approaches for converting any variable selection into on that controls false discovery rate (FDR).
Simple Bayesian Algorithms for Best Arm Identification | March 9, 2021
This week we reviewed techniques using simple Bayesian algorithms for sequential decision-making problems.
glmnet | February 23, 2021
This week, we discuss glment, the widely-renowned, frequently-used, and efficient Lasso optimization package.
Prophet | February 9, 2021
In this conversation, we take a look at Prophet, an automatic, open-source, time-series forecasting tool by Facebook.
Stability Selection (Error Control) | January 25, 2021
A look at Stability Selection, an extremely general finite sample control technique for structure estimation. The main result we'll drive towards is an error control bound for the expected number of false discoveries.
R-Learner | December 7, 2020
A discussion on R-learner, a 2-step causal inference algorithm to estimate heterogeneous treatment effects from observational data.
Fixed-X knockoffs | November 9, 2020
A look at a novel method for False Discovery Rate control in variable selection — the Fixed-X Knockoff filter by Rina Barber and Emmanuel Candès.
Quasi-Newton part two: BFGS | October 27, 2020
A discussion of Quasi-Newton methods that create approximations that meet this criterion and thus enjoy global and local convergence properties.
Quasi-Newton part one: Wolfe conditions | October 13, 2020
The first part in a series of papers we're reading on Quasi-Newton methods, which Sisu relies on for optimizing key subproblems when running workflows.
Benjamini-Hochberg | August 17, 2020
A discussion on Benjamini-Hochberg, avoiding the multi-comparison problem, and False Discovery Rate (FDR).
SCANN | August 3, 2020
This week, we take a look at ScaNN (Scalable Nearest Neighbors), a method for efficient vector similarity search at scale.
The Synthetic Controls Method | July 6, 2020
In this weeks discussion, we review the Synthetic Controls method, which extends potential outcomes form Causal Inference literature to time-dependent observational data.