no code implementations • 13 Feb 2024 • Haolin Zou, Arnab Auddy, Kamiar Rahnama Rad, Arian Maleki
Despite a large and significant body of recent work focused on estimating the out-of-sample risk of regularized models in the high dimensional regime, a theoretical understanding of this problem for non-differentiable penalties such as generalized LASSO and nuclear norm is missing.
no code implementations • 26 Oct 2023 • Arnab Auddy, Haolin Zou, Kamiar Rahnama Rad, Arian Maleki
Recent theoretical work showed that approximate leave-one-out cross validation (ALO) is a computationally efficient and statistically reliable estimate of LO (and OO) for generalized linear models with differentiable regularizers.
no code implementations • 31 Mar 2023 • Arnab Auddy, Ming Yuan
Our method is fairly easy to implement and numerical experiments are presented to further demonstrate its practical merits.
no code implementations • 20 Jul 2021 • Arnab Auddy, Ming Yuan
In this paper, we study the estimation of a rank-one spiked tensor in the presence of heavy tailed noise.
no code implementations • 17 Jul 2020 • Arnab Auddy, Ming Yuan
We develop deterministic perturbation bounds for singular values and vectors of orthogonally decomposable tensors, in a spirit similar to classical results for matrices such as those due to Weyl, Davis, Kahan and Wedin.