On Dynamic Regret and Constraint Violations in Constrained Online Convex Optimization

01/24/2023
by   Rahul Vaze, et al.
0

A constrained version of the online convex optimization (OCO) problem is considered. With slotted time, for each slot, first an action is chosen. Subsequently the loss function and the constraint violation penalty evaluated at the chosen action point is revealed. For each slot, both the loss function as well as the function defining the constraint set is assumed to be smooth and strongly convex. In addition, once an action is chosen, local information about a feasible set within a small neighborhood of the current action is also revealed. An algorithm is allowed to compute at most one gradient at its point of choice given the described feedback to choose the next action. The goal of an algorithm is to simultaneously minimize the dynamic regret (loss incurred compared to the oracle's loss) and the constraint violation penalty (penalty accrued compared to the oracle's penalty). We propose an algorithm that follows projected gradient descent over a suitably chosen set around the current action. We show that both the dynamic regret and the constraint violation is order-wise bounded by the path-length, the sum of the distances between the consecutive optimal actions. Moreover, we show that the derived bounds are the best possible.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/09/2021

Delay-Tolerant Constrained OCO with Application to Network Resource Allocation

We consider online convex optimization (OCO) with multi-slot feedback de...
research
01/14/2017

An Online Convex Optimization Approach to Dynamic Network Resource Allocation

Existing approaches to online convex optimization (OCO) make sequential ...
research
05/01/2021

Regret and Cumulative Constraint Violation Analysis for Distributed Online Constrained Convex Optimization

This paper considers the distributed online convex optimization problem ...
research
11/14/2021

Safe Online Convex Optimization with Unknown Linear Safety Constraints

We study the problem of safe online convex optimization, where the actio...
research
06/13/2018

Minimizing Regret in Bandit Online Optimization in Unconstrained and Constrained Action Spaces

We consider online convex optimization with zeroth-order feedback settin...
research
03/28/2018

Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descent

We study Smoothed Online Convex Optimization, a version of online convex...
research
01/26/2023

Online Convex Optimization with Stochastic Constraints: Zero Constraint Violation and Bandit Feedback

This paper studies online convex optimization with stochastic constraint...

Please sign up or login with your details

Forgot password? Click here to reset