no code implementations • 15 Nov 2023 • Felix Abramovich
We consider a deep neural network estimator based on empirical risk minimization with l_1-regularization.
no code implementations • 4 Dec 2022 • Felix Abramovich
We consider (nonparametric) sparse additive models (SpAM) for classification.
no code implementations • 13 Apr 2022 • Tomer Levy, Felix Abramovich
We consider high-dimensional multiclass classification by sparse multinomial logistic regression.
no code implementations • 4 Mar 2020 • Felix Abramovich, Vadim Grinshtein, Tomer Levy
We propose first a feature selection procedure based on penalized maximum likelihood with a complexity penalty on the model size and derive the nonasymptotic bounds for misclassification excess risk of the resulting classifier.
1 code implementation • 26 Jun 2017 • Felix Abramovich, Vadim Grinshtein
To find a model selection procedure computationally feasible for high-dimensional data, we extend the Slope estimator for logistic regression and show that under an additional weighted restricted eigenvalue condition it is rate-optimal in the minimax sense.
no code implementations • 4 Jun 2015 • Felix Abramovich, Marianna Pensky
The objective of the paper is to study accuracy of multi-class classification in high-dimensional setting, where the number of classes is also large ("large $L$, large $p$, small $n$" model).