Modifying Squint for Prediction with Expert Advice in a Changing Environment
This work addresses a domain-specific issue for online learning practitioners, offering an incremental improvement by modifying an existing algorithm to handle environmental changes.
The paper tackles the problem of adapting the Squint algorithm for prediction with expert advice to changing environments, resulting in Squint-CE, which preserves Squint's beneficial properties like performing at least as well as other algorithms in non-changing settings.
We provide a new method for online learning, specifically prediction with expert advice, in a changing environment. In a non-changing environment the Squint algorithm has been designed to always function at least as well as other known algorithms and in specific cases it functions much better. However, when using a conventional black-box algorithm to make Squint suitable for a changing environment, it loses its beneficial properties. Hence, we provide a new algorithm, Squint-CE, which is suitable for a changing environment and preserves the properties of Squint.