Mathematical optimization is one of the cornerstones of modern engineering research and
practice. Yet, throughout all application domains, mathematical optimization is, for the most …

A central capability of intelligent systems is the ability to continuously build upon previous
experiences to speed up and enhance learning of new tasks. Two distinct research …

Incremental learning refers to learning from streaming data, which arrive over time, with
limited memory resources and, ideally, without sacrificing model accuracy. This setting fits …

This work addresses decentralized online optimization in nonstationary environments. A
network of agents aim to track the minimizer of a global, time-varying, and convex function …

This paper considers distributed online optimization with time-varying coupled inequality
constraints. The global objective function is composed of local convex cost and …

Existing approaches to online convex optimization make sequential one-slot-ahead
decisions, which lead to (possibly adversarial) losses that drive subsequent decision …

In this paper, we address tracking of a time-varying parameter with unknown dynamics. We
formalize the problem as an instance of online optimization in a dynamic setting. Using …

This paper deals with online convex optimization involving both time-varying loss functions,
and time-varying constraints. The loss functions are not fully accessible to the learner, and …

In this paper, online convex optimization problem with time-varying constraints is studied
from the perspective of an agent taking sequential actions. Both the objective function and …

We consider nondifferentiable dynamic optimization problems such as those arising in
robotics and subspace tracking. Given the computational constraints and the time-varying …