BFE and AdaBFE: A New Approach in Learning Rate Automation for Stochastic Optimization
This provides a heuristic approach for researchers in machine learning to improve gradient-based optimization, though it is incremental as it offers a different perspective rather than aiming to beat benchmarks.
The paper tackles the problem of automating learning rates in stochastic optimization by proposing BFE for non-adaptive and AdaBFE for adaptive learning rates, offering an alternative perspective to existing methods like SGD and Adam, with comparative studies included.
In this paper, a new gradient-based optimization approach by automatically adjusting the learning rate is proposed. This approach can be applied to design non-adaptive learning rate and adaptive learning rate. Firstly, I will introduce the non-adaptive learning rate optimization method: Binary Forward Exploration (BFE), and then the corresponding adaptive per-parameter learning rate method: Adaptive BFE (AdaBFE) is possible to be developed. This approach could be an alternative method to optimize the learning rate based on the stochastic gradient descent (SGD) algorithm besides the current non-adaptive learning rate methods e.g. SGD, momentum, Nesterov and the adaptive learning rate methods e.g. AdaGrad, AdaDelta, Adam... The purpose to develop this approach is not to beat the benchmark of other methods but just to provide a different perspective to optimize the gradient descent method, although some comparative study with previous methods will be made in the following sections. This approach is expected to be heuristic or inspire researchers to improve gradient-based optimization combined with previous methods.