Online Optimization in Dynamic Environments

By Eric C. Hall, Rebecca M. Willett. 2013

29 citations recorded by the source corpus.

High-velocity streams of high-dimensional data pose significant "big data" analysis challenges across a range of applications and settings. Online learning and online convex programming play a significant role in the rapid recovery of important or anomalous information from these large datastreams. While recent advances in online learning have led to novel and rapidly converging algorithms, these methods are unable to adapt to nonstationary environments arising in real-world problems. This paper describes a dynamic mirror descent framework which addresses this challenge, yielding low theoretical regret bounds and accurate, adaptive, and computationally efficient algorithms which are applicable to broad classes of problems. The methods are capable of learning and adapting to an underlying and possibly time-varying dynamical model. Empirical results in the context of dynamic texture analysis, solar flare detection, sequential compressed sensing of a dynamic scene, traffic surveillance,tracking self-exciting point processes and network behavior in the Enron email corpus support the core theoretical findings.

Subfields: Artificial Intelligence, Computational Mechanics, Management Science and Operations Research

How researchers see this paper

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

In Artificial Intelligence

In Computational Mechanics

In Management Science and Operations Research

Citations in the corpus

Adaptive Gradient-Based Meta-Learning Methods (2019, background): “The generality of ARUBA also allows for the incorporation of other dynamic regret bounds [25, 52] and other non-static notions of regret [27].”
Competing with Automata-based Expert Sequences (2018, background): “Another assumes that the learner has access to a dynamical model that is able to capture the benchmark sequence [Hall and Willett, 2013].”
Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient (2016, background): “A more general variation is considered in (Hall & Willett, 2013), where a sequence of (or a family of) dynamic models φ 1 , . . . , φ T are revealed by the environment for the learner to predict the decision in the next step.”