2 papers
cs.LG2026
Combining Adam and its Inverse Counterpart to Enhance Generalization of Deep Learning Optimizers
Tao Shi, Liangming Chen, Long Jin +1
In the training of neural networks, adaptive moment estimation (Adam) typically converges fast but exhibits suboptimal generalization performance. A widely accepted explanation for…
cs.LG2024
A Method for Enhancing Generalization of Adam by Multiple Integrations
Long Jin, Han Nong, Liangming Chen +1
The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly…