Efficient Online Convex Optimization with Adaptively Minimax Optimal Dynamic Regret

30 Jun 2019Hakan GokcesuS. Serdar Kozat

We introduce an online convex optimization algorithm using projected sub-gradient descent with ideal adaptive learning rates, where each computation is efficiently done in a sequential manner. For the first time in the literature, this algorithm provides an adaptively minimax optimal dynamic regret guarantee for a sequence of convex functions without any restrictions -- such as strong convexity, smoothness or even Lipschitz continuity -- against a comparator decision sequence with bounded total successive changes... (read more)

PDF Abstract


No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.