4.6 Article

Enhancing deep learning algorithm accuracy and stability using multicriteria optimization: an application to distributed learning with MNIST digits

Journal

ANNALS OF OPERATIONS RESEARCH
Volume -, Issue -, Pages -

Publisher

SPRINGER
DOI: 10.1007/s10479-022-04833-x

Keywords

Artificial intelligence; Deep learning; Machine learning; Multicriteria optimization; Classification; MINST data

Ask authors/readers for more resources

The article discusses the importance of the training phase in machine learning, presents an innovative model for learning with multiple data sets using multi-criteria optimization techniques, and discusses the stability results of effective solutions in the presence of input and output data perturbations.
The training phase is the most crucial stage during the machine learning process. In the case of labeled data and supervised learning, machine learning entails minimizing the loss function under various constraints. We provide an innovative model for learning with numerous data sets, resulting from the application of multicriteria optimization techniques to existing deep learning algorithms. Data fitting is formulated as a multicriteria model in which each criterion measures the data fitting error on a specific data set. This is an optimization model involving a vector-valued function, and it has to be analyzed using the notion of Pareto efficiency. We present stability results for efficient solutions in the presence of input and output data perturbations. The multiple data set environment comes into play to eliminate the bias caused by the selection of a specific training set. To apply this concept, we present a scalarization strategy as well as numerical experiments in digit classification using MNIST data.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available