P Patil, JH Du - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
We establish precise structural and risk equivalences between subsampling and ridge regularization for ensemble ridge estimators. Specifically, we prove that linear and quadratic …
Bagging is an important technique for stabilizing machine learning models. In this paper, we derive a finite-sample guarantee on the stability of bagging for any model. Our result places …
While effective in practice, iterative methods for solving large systems of linear equations can be significantly affected by problem-dependent condition number quantities. This makes …
P Patil, D LeJeune - arXiv preprint arXiv:2310.04357, 2023 - arxiv.org
We employ random matrix theory to establish consistency of generalized cross validation (GCV) for estimating prediction risks of sketched ridge regression ensembles, enabling …
We study the behavior of optimal ridge regularization and optimal ridge risk for out-of- distribution prediction, where the test distribution deviates arbitrarily from the train …
Bagging is an important technique for stabilizing machine learning models. In this paper, we derive a finite-sample guarantee on the stability of bagging for any model. Our result places …
Matrix sketching is a powerful tool for reducing the size of large data matrices. Yet there are fundamental limitations to this size reduction when we want to recover an accurate estimator …
A Complete Bibliography of Publications in the SIAM Journal on Mathematics of Data Science Page 1 A Complete Bibliography of Publications in the SIAM Journal on Mathematics of Data …