3 papers
math.ST2025
From Graphical Lasso to Atomic Norms: High-Dimensional Pattern Recovery
Piotr Graczyk, Bartosz Kołodziejek, Hideto Nakashima +1
We study high-dimensional precision-matrix estimation with polyhedral atomic-norm penalties on the off-diagonal entries. This framework covers the graphical lasso, -ty…
math.ST2022
Pattern recovery by SLOPE
Małgorzata Bogdan, Xavier Dupuis, Piotr Graczyk +4
SLOPE is a popular method for dimensionality reduction in the high-dimensional regression. Indeed some regression coefficient estimates of SLOPE can be null (sparsity) or can be eq…
math.ST2022
Pattern recovery and signal denoising by SLOPE when the design matrix is orthogonal
Tomasz Skalski, Piotr Graczyk, Bartosz Kołodziejek +1
Sorted Penalized Estimator (SLOPE) is a relatively new convex regularization method for fitting high-dimensional regression models. SLOPE allows to reduce the model dimens…