Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022
Dynamic Regret of Adaptive Gradient Methods for Strongly Convex Problems
Parvin Nazari, Esmaile Khorram
Adaptive gradient algorithms such as ADAGRAD and its variants have gained popularity in the training of deep neural networks. While many works as for adaptive methods have focused…
cs.LG2021
Dynamic Regret Analysis for Online Meta-Learning
Parvin Nazari, Esmaile Khorram
The online meta-learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for an agent is to quickly learn new tasks by drawing on prio…