Towards Stability of Parameter-free Optimization
Pang, Yijiang, Yu, Shuyang, Hoang, Bao, Zhou, Jiayu
–arXiv.org Artificial Intelligence
Hyperparameter tuning, particularly the selection of an appropriate learning rate in adaptive gradient training methods, remains a challenge. To tackle this challenge, in this paper, we propose a novel parameter-free optimizer, \textsc{AdamG} (Adam with the golden step size), designed to automatically adapt to diverse optimization problems without manual tuning. The core technique underlying \textsc{AdamG} is our golden step size derived for the AdaGrad-Norm algorithm, which is expected to help AdaGrad-Norm preserve the tuning-free convergence and approximate the optimal step size in expectation w.r.t. various optimization scenarios. To better evaluate tuning-free performance, we propose a novel evaluation criterion, \textit{reliability}, to comprehensively assess the efficacy of parameter-free optimizers in addition to classical performance criteria. Empirical results demonstrate that compared with other parameter-free baselines, \textsc{AdamG} achieves superior performance, which is consistently on par with Adam using a manually tuned learning rate across various optimization tasks.
arXiv.org Artificial Intelligence
May-27-2024
- Country:
- North America
- Canada > Ontario
- Toronto (0.14)
- United States > Michigan
- Ingham County (0.14)
- Canada > Ontario
- North America
- Genre:
- Research Report > New Finding (0.48)
- Technology: