MADA: Meta-Adaptive Optimizers through hyper-gradient Descent

arXiv:2401.08893v2 Announce Type: replace
Abstract: Since Adam was introduced, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this work, we introduce Meta-Adaptive Optimizers (MADA), a unified optimizer framework that can generalize several known optimizers and dynamically learn the most suitable one during training. The key idea in MADA is to parameterize the space of optimizers and search through it using hyper-gradient …

abstract adam arxiv cs.lg deep learning excel framework gradient math.oc meta novel tasks through type work