Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descent
This work addresses a fundamental problem in online optimization for scenarios with switching penalties, offering significant theoretical advances for researchers in machine learning and optimization.
The paper tackles Smoothed Online Convex Optimization by introducing Online Balanced Descent (OBD), a framework that balances switching and hitting costs to achieve a dimension-free competitive ratio of 3 + O(1/α) for locally polyhedral costs, improving upon previous bounds.
We study Smoothed Online Convex Optimization, a version of online convex optimization where the learner incurs a penalty for changing her actions between rounds. Given a $Ω(\sqrt{d})$ lower bound on the competitive ratio of any online algorithm, where $d$ is the dimension of the action space, we ask under what conditions this bound can be beaten. We introduce a novel algorithmic framework for this problem, Online Balanced Descent (OBD), which works by iteratively projecting the previous point onto a carefully chosen level set of the current cost function so as to balance the switching costs and hitting costs. We demonstrate the generality of the OBD framework by showing how, with different choices of "balance," OBD can improve upon state-of-the-art performance guarantees for both competitive ratio and regret, in particular, OBD is the first algorithm to achieve a dimension-free competitive ratio, $3 + O(1/α)$, for locally polyhedral costs, where $α$ measures the "steepness" of the costs. We also prove bounds on the dynamic regret of OBD when the balance is performed in the dual space that are dimension-free and imply that OBD has sublinear static regret.