Online Learning of Non-stationary Sequences

By Claire Monteleoni, Tommi S. Jaakkola. 2003

61 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams (2020, background): “However, online learning typically makes the rigorous assumption of learning from an iid data stream [41] or does not focus on preventing catastrophic forgetting [34, 26], whereas data incremental learning disregards the iid assumption and additionally generalizes beyond the online learning horizon ”
Competing with Automata-based Expert Sequences (2018, methodology): “In particular, they showed how algorithms designed for k-shifting regret, e.g. [Herbster and Warmuth, 1998, Monteleoni and Jaakkola, 2003], can be interpreted as specific priors in this formulation.”
Dynamic Weighted Majority: An Ensemble Method for Drifting Concepts (2007, background): “There has also been theoretical work on this problem (e.g., Helmbold and Long, 1991; Kuh et al., 1991; Helmbold and Long, 1994; Auer and Warmuth, 1998; Mesterharm, 2003; Monteleoni and Jaakkola, 2004; Kolter and Maloof, 2005), but a thorough survey of this work is beyond the scope of the paper.”
Tackling Climate Change with Machine Learning (2019, background): “[458]) could select the best-performing model at any given point in time [459]; this idea has been refined in further work [460, 461].”
Efficient Tracking of Large Classes of Experts (2011, unknown): “(10) This, together with (9), implies (8).”
Nearly Tight Bounds for the Continuum-Armed Bandit Problem (2004, background): “In addition to occupying a central position in online learning theory, algorithms for such problems have been applied in numerous other areas of computer science, such as paging and caching [6, 14], data structures [7], routing [4, 5], wireless networks [19], and online auction mechanisms [8, 15].”
A Closer Look at Adaptive Regret (2012, background): “2 Example 2: Slowly Decreasing Switching Rate The idea of slowly decreasing the switching rate was considered by Shamir and Merhav (1999) in the context of source coding, and later analysed for expert switching by Koolen and De Rooij (2008); we saw in Section 3.”