CoRe Optimizer: An All-in-One Solution for Machine Learning
This work addresses the need for efficient and general-purpose optimizers in machine learning, though it appears incremental as it builds on existing first-order gradient-based methods.
The paper tackles the problem of optimizing machine learning models by introducing the CoRe optimizer, which achieves best or competitive performance across diverse tasks while requiring minimal hyperparameter tuning.
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.