Reviews: Dynamic Local Regret for Non-convex Online Forecasting

This paper considers online forecasting problems with non-convex models. One of the main challenges in forecasting is concept drift, which refers to changes in the underlying relationship between inputs and outputs over time. Classic online learning algorithms have performance bounds in terms of regret, which compares the algorithm's performance to the best fixed action in hindsight. While regret makes sense when losses are convex, it is no longer appealing when there are non-convex losses. Hazan et al. 2017 introduced a notion of local regret to be used for online non-convex problems, as well as algorithms that achieve sublinear local regret.