Bandit Convex Optimisation

The recent publication on bandit convex optimisation outlines a fundamental framework for zeroth-order convex optimisation, detailing various techniques including cutting plane methods, interior point methods, continuous exponential weights, gradient descent, and online Newton steps. Although the article notes that there is not much truly new in the field, it emphasizes the innovative application of existing tools to derive new algorithms and improve some bounds slightly. This work is significant as it contributes to the ongoing discourse in optimisation methods, providing insights that can enhance algorithmic performance and efficiency. The relevance of these advancements is underscored by their potential applications in various domains, thereby reinforcing the importance of continuous exploration and refinement in optimisation strategies.