Online Optimization with Feedback Delay and Nonlinear Switching Cost

10/29/2021
by   Weici Pan, et al.
0

We study a variant of online optimization in which the learner receives k-round delayed feedback about hitting cost and there is a multi-step nonlinear switching cost, i.e., costs depend on multiple previous actions in a nonlinear manner. Our main result shows that a novel Iterative Regularized Online Balanced Descent (iROBD) algorithm has a constant, dimension-free competitive ratio that is O(L^2k), where L is the Lipschitz constant of the switching cost. Additionally, we provide lower bounds that illustrate the Lipschitz condition is required and the dependencies on k and L are tight. Finally, via reductions, we show that this setting is closely related to online control problems with delay, nonlinear dynamics, and adversarial disturbances, where iROBD directly offers constant-competitive online policies.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/23/2018

Smoothed Online Optimization for Regression and Control

We consider Online Convex Optimization (OCO) in the setting where the co...
research
05/29/2019

Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization

We study online convex optimization in a setting where the learner seeks...
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
02/13/2020

Beyond No-Regret: Competitive Control via Online Optimization with Memory

This paper studies online control with adversarial disturbances using to...
research
02/13/2021

Revisiting Smoothed Online Learning

In this paper, we revisit the problem of smoothed online learning, in wh...
research
11/10/2019

Online Optimization with Predictions and Non-convex Losses

We study online optimization in a setting where an online learner seeks ...
research
05/02/2022

Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor

In this paper, we investigate an online prediction strategy named as Dis...

Please sign up or login with your details

Forgot password? Click here to reset