Skip to main content
. Author manuscript; available in PMC: 2022 Sep 8.
Published in final edited form as: Ann Appl Stat. 2022 Jul 19;16(3):1891–1918. doi: 10.1214/21-aoas1575

Fig. 3.

Fig. 3.

R2 each run is evaluated on a test set of size 5000. “oracle” is the result where we know the true active variables and solve on this subset of variables. “glmnet” fits the responses separately. “SRRR-r” indicates the SRRR results with assumed rank r.