CoRe Optimizer: An All-in-One Solution for Machine Learning

TL;DR

The paper introduces the CoRe optimizer, a versatile and efficient algorithm that outperforms or matches existing optimizers across various machine learning tasks, with minimal hyperparameter tuning.

Contribution

It provides an extensive comparison of CoRe with nine other optimizers and offers generally applicable hyperparameter settings for diverse applications.

Findings

CoRe outperforms other optimizers in multiple tasks

Only one hyperparameter needs adjustment for different learning modes

CoRe achieves fast, smooth convergence with low computational demand

Abstract

The optimization algorithm and its hyperparameters can significantly affect the training speed and resulting model accuracy in machine learning applications. The wish list for an ideal optimizer includes fast and smooth convergence to low error, low computational demand, and general applicability. Our recently introduced continual resilient (CoRe) optimizer has shown superior performance compared to other state-of-the-art first-order gradient-based optimizers for training lifelong machine learning potentials. In this work we provide an extensive performance comparison of the CoRe optimizer and nine other optimization algorithms including the Adam optimizer and resilient backpropagation (RPROP) for diverse machine learning tasks. We analyze the influence of different hyperparameters and provide generally applicable values. The CoRe optimizer yields best or competitive performance in every investigated application, while only one hyperparameter needs to be changed depending on mini-batch or batch learning.