Mahsa Yousefi

According to our database, Mahsa Yousefi authored at least 10 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Fully stochastic trust-region methods with Barzilai-Borwein steplengths.

Stefania Bellavia, Benedetta Morini, Mahsa Yousefi

J. Comput. Appl. Math., 2026

2025

Soil Analysis with Machine-Learning-Based Processing of Air-Coupled Stepped-Frequency GPR Field Measurements: Preliminary Study.

Chunlei Xu, Michael Pregesbauer, Naga Sravani Chilukuri, Daniel Windhager, Mahsa Yousefi, Pedro Julián, Lothar Ratschbacher

Proceedings of the 33rd European Signal Processing Conference, 2025

2024

A non-monotone trust-region method with noisy oracles and additional sampling.

Natasa Krejic, Natasa Krklec Jerinkic, Angeles Martinez, Mahsa Yousefi

Comput. Optim. Appl., September, 2024

Soil analysis with machine-learning-based processing of stepped-frequency GPR field measurements: Preliminary study.

Chunlei Xu, Michael Pregesbauer, Naga Sravani Chilukuri, Daniel Windhager, Mahsa Yousefi, Pedro Julián, Lothar Ratschbacher

CoRR, 2024

2023

Majorization-Minimization for sparse SVMs.

Alessandro Benfenati, Emilie Chouzenoux, Giorgia Franchini, Salla Latva-Aijo, Dominik Narnhofer, Jean-Christophe Pesquet, Sebastian J. Scott, Mahsa Yousefi

CoRR, 2023

Deep Neural Networks Training by Stochastic Quasi-Newton Trust-Region Methods.

Mahsa Yousefi, Angeles Martinez

Algorithms, 2023

Combined First- and Second-Order Directions for Deep Neural Networks Training.

Ángeles Martínez, Marco Viola, Mahsa Yousefi

Proceedings of the Numerical Computations: Theory and Algorithms, 2023

2022

On the efficiency of Stochastic Quasi-Newton Methods for Deep Learning.

Mahsa Yousefi, Angeles Martinez

CoRR, 2022

A stochastic nonmonotone trust-region training algorithm for image classification.

Mahsa Yousefi, Ángeles Martínez Calomardo

Proceedings of the 16th International Conference on Signal-Image Technology & Internet-Based Systems, 2022

A Stochastic Modified Limited Memory BFGS for Training Deep Neural Networks.

Mahsa Yousefi, Ángeles Martínez Calomardo

Proceedings of the Intelligent Computing, 2022