Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Rad, Kamiar Rahnama"'
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 LA
Externí odkaz:
http://arxiv.org/abs/2402.08543
The out-of-sample error (OO) is the main quantity of interest in risk estimation and model selection. Leave-one-out cross validation (LO) offers a (nearly) distribution-free yet computationally demanding approach to estimate OO. Recent theoretical wo
Externí odkaz:
http://arxiv.org/abs/2310.17629
Publikováno v:
AISTATS 2020
We study the problem of out-of-sample risk estimation in the high dimensional regime where both the sample size $n$ and number of features $p$ are large, and $n/p$ can be less than one. Extensive empirical evidence confirms the accuracy of leave-one-
Externí odkaz:
http://arxiv.org/abs/2003.01770
Risk estimation is at the core of many learning systems. The importance of this problem has motivated researchers to propose different schemes, such as cross validation, generalized cross validation, and Bootstrap. The theoretical properties of such
Externí odkaz:
http://arxiv.org/abs/1902.01753
Autor:
Rad, Kamiar Rahnama, Maleki, Arian
The paper considers the problem of out-of-sample risk estimation under the high dimensional settings where standard techniques such as $K$-fold cross validation suffer from large biases. Motivated by the low bias of the leave-one-out cross validation
Externí odkaz:
http://arxiv.org/abs/1801.10243
A common analytical problem in neuroscience is the interpretation of neural activity with respect to sensory input or behavioral output. This is typically achieved by regressing measured neural activity against known stimuli or behavioral variables t
Externí odkaz:
http://arxiv.org/abs/1606.07845
Publikováno v:
IEEE Transactions on Information Theory; November 2024, Vol. 70 Issue: 11 p8040-8071, 32p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Rad, Kamiar Rahnama
Consider the $n$-dimensional vector $y=X\be+\e$, where $\be \in \R^p$ has only $k$ nonzero entries and $\e \in \R^n$ is a Gaussian noise. This can be viewed as a linear system with sparsity constraints, corrupted by noise. We find a non-asymptotic up
Externí odkaz:
http://arxiv.org/abs/0910.0456
Publikováno v:
The Annals of Applied Statistics, 2017 Jun 01. 11(2), 598-637.
Externí odkaz:
https://www.jstor.org/stable/26362198