no code implementations • 13 Mar 2024 • Mohammad Lashkari, Amin Gheibi
The generalization performance of deep neural networks in classification tasks is a major concern in machine learning research.
no code implementations • 29 Mar 2023 • Mohammad Lashkari, Amin Gheibi
In this paper, we theoretically prove that the Lipschitz constant of a loss function is an important factor to diminish the generalization error of the output model obtained by Adam or AdamW.