Handling Delayed Feedback in Distributed Online Optimization : A Projection-Free Approach
This work addresses the need for simple, robust, and reliable algorithms for distributed learning at the edges, particularly under network delays, with incremental improvements in handling delays in optimization.
The authors tackled the problem of online convex optimization with adversarial delayed feedback by proposing projection-free algorithms for centralized and distributed settings, achieving an optimal regret bound of O(√B) where B is the sum of delays.
Learning at the edges has become increasingly important as large quantities of data are continually generated locally. Among others, this paradigm requires algorithms that are simple (so that they can be executed by local devices), robust (again uncertainty as data are continually generated), and reliable in a distributed manner under network issues, especially delays. In this study, we investigate the problem of online convex optimization under adversarial delayed feedback. We propose two projection-free algorithms for centralised and distributed settings in which they are carefully designed to achieve a regret bound of O(\sqrt{B}) where B is the sum of delay, which is optimal for the OCO problem in the delay setting while still being projection-free. We provide an extensive theoretical study and experimentally validate the performance of our algorithms by comparing them with existing ones on real-world problems.