Modifying Squint for Prediction with Expert Advice in a Changing Environment

TL;DR

This paper introduces Squint-CE, an adaptation of the Squint algorithm, designed for online prediction with expert advice in dynamic environments, maintaining Squint's advantages while handling environmental changes.

Contribution

The paper presents Squint-CE, a novel algorithm that extends Squint's capabilities to changing environments without losing its original benefits.

Findings

Squint-CE performs well in changing environments.

It retains Squint's original advantages.

The algorithm adapts effectively to environmental shifts.

Abstract

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.