Search Results for author: Felix Abramovich

Found 6 papers, 1 papers with code

Statistical learning by sparse deep neural networks

no code implementations15 Nov 2023 Felix Abramovich

We consider a deep neural network estimator based on empirical risk minimization with l_1-regularization.

regression

Classification by sparse additive models

no code implementations4 Dec 2022 Felix Abramovich

We consider (nonparametric) sparse additive models (SpAM) for classification.

Additive models Classification

Generalization Error Bounds for Multiclass Sparse Linear Classifiers

no code implementations13 Apr 2022 Tomer Levy, Felix Abramovich

We consider high-dimensional multiclass classification by sparse multinomial logistic regression.

Binary Classification feature selection +1

Multiclass classification by sparse multinomial logistic regression

no code implementations4 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.

Classification feature selection +2

High-dimensional classification by sparse logistic regression

1 code implementation26 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.

Binary Classification Classification +5

Classification with many classes: challenges and pluses

no code implementations4 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).

Classification feature selection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.