AdamZ: An Enhanced Optimisation Method for Neural Network Training
This work addresses optimization challenges for neural network training, but it is incremental as it builds on the existing Adam optimizer.
The paper tackles the problem of overshooting and stagnation in neural network training by introducing AdamZ, an enhanced variant of the Adam optimizer that dynamically adjusts the learning rate, resulting in improved model performance across diverse tasks.
AdamZ is an advanced variant of the Adam optimiser, developed to enhance convergence efficiency in neural network training. This optimiser dynamically adjusts the learning rate by incorporating mechanisms to address overshooting and stagnation, that are common challenges in optimisation. Specifically, AdamZ reduces the learning rate when overshooting is detected and increases it during periods of stagnation, utilising hyperparameters such as overshoot and stagnation factors, thresholds, and patience levels to guide these adjustments. While AdamZ may lead to slightly longer training times compared to some other optimisers, it consistently excels in minimising the loss function, making it particularly advantageous for applications where precision is critical. Benchmarking results demonstrate the effectiveness of AdamZ in maintaining optimal learning rates, leading to improved model performance across diverse tasks.