2 papers
cs.CV2025
Efficient Training of Deep Networks using Guided Spectral Data Selection: A Step Toward Learning What You Need
Mohammadreza Sharifi, Ahad Harati
Effective data curation is essential for optimizing neural network training. In this paper, we present the Guided Spectrally Tuned Data Selection (GSTDS) algorithm, which dynamical…
cs.LG2024
Optimizing Data Curation through Spectral Analysis and Joint Batch Selection (SALN)
Mohammadreza Sharifi
In modern deep learning models, long training times and large datasets present significant challenges to both efficiency and scalability. Effective data curation and sample selecti…