To Raise or Not To Raise: The Autonomous Learning Rate Question
This addresses the time-consuming and unstable process of learning rate selection for deep learning practitioners, though it appears incremental as it builds on existing optimization techniques.
The paper tackles the problem of manually tuning learning rates in deep learning, which is tedious and sensitive to changes in model or data, by proposing an Autonomous Learning Rate Controller that automatically adjusts the learning rate during training.
There is a parameter ubiquitous throughout the deep learning world: learning rate. There is likewise a ubiquitous question: what should that learning rate be? The true answer to this question is often tedious and time consuming to obtain, and a great deal of arcane knowledge has accumulated in recent years over how to pick and modify learning rates to achieve optimal training performance. Moreover, the long hours spent carefully crafting the perfect learning rate can come to nothing the moment your network architecture, optimizer, dataset, or initial conditions change ever so slightly. But it need not be this way. We propose a new answer to the great learning rate question: the Autonomous Learning Rate Controller. Find it at https://github.com/fastestimator/ARC/tree/v2.0