Uniform Wrappers: Bridging Concave to Quadratizable Functions in Online Optimization

This paper presents novel contributions to the field of online optimization, particularly focusing on the adaptation of algorithms from concave optimization to more challenging classes of functions. Key contributions include the introduction of uniform wrappers, a class of meta-algorithms that could be used for algorithmic conversions such as converting algorithms for convex optimization into those for quadratizable optimization. Moreover, we propose a guideline that, given a base algorithm A for concave optimization and a uniform wrapper W , describes how to convert a proof of the regret bound of A in the concave setting into a proof of the regret bound of W ( A ) for quadratizable setting. Through this framework, the paper demonstrates improved regret guarantees for various classes of DR-submodular functions under zeroth-order feedback. Furthermore, the paper extends zeroth-order online algorithms to bandit feedback and offline counter-parts, achieving notable improvements in regret/sample complexity compared to existing approaches.