In online learning problems, exploiting low variance plays an important role in obtaining tight performance guarantees yet ischallenging because variances are often not known a priori. Recently, considerable progress has been made by Zhangetal.

In2013, theshort-term tracking (STT) task and related benchmarks were proposed [6,7,8].

We introduce a simple sequence model inspired by control systems thatgeneralizes these approaches while addressing their shortcomings.

Between 2018 and 2020, the field witnessed asurgein the development of these models (Devlin etal.,2019;Liu