English

Towards Stability of Parameter-free Optimization

Machine Learning 2024-05-28 v3

Abstract

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.

Keywords

Cite

@article{arxiv.2405.04376,
  title  = {Towards Stability of Parameter-free Optimization},
  author = {Yijiang Pang and Shuyang Yu and Bao Hoang and Jiayu Zhou},
  journal= {arXiv preprint arXiv:2405.04376},
  year   = {2024}
}
R2 v1 2026-06-28T16:19:35.433Z