Editorial Notes
RETRACTION NOTICE: "On the Value of Look-Ahead in Competitive Online Convex Optimization," by Shi et al., Proceedings of the ACM on Measurement and Analysis of Computing Systems, Volume 3, Issue 2, Article No. 22, has been retracted at the request of the authors because they found a critical mistake in the main result Theorem 3.1.
Abstract
RETRACTION NOTICE: "On the Value of Look-Ahead in Competitive Online Convex Optimization," by Shi et al., Proceedings of the ACM on Measurement and Analysis of Computing Systems, Volume 3, Issue 2, Article No. 22, has been retracted at the request of the authors because they found a critical mistake in the main result Theorem 3.1.
https://dl.acm.org/doi/10.1145/3341617.3326136
Supplemental Material
Available for Download
Notice of Retraction for "On the Value of Look-Ahead in Competitive Online Convex Optimization" by Shi et al., Proceedings of the ACM on Measurement and Analysis of Computing System, Volume 3, Issue 2 (POMACS 3:2).
Index Terms
Retracted on December 2, 2020: On the Value of Look-Ahead in Competitive Online Convex Optimization
Recommendations
Online Optimization with Predictions and Non-convex Losses
SIGMETRICSWe study online optimization in a setting where an online learner seeks to optimize a per-round hitting cost, which may be non-convex, while incurring a movement cost when changing actions between rounds. We ask:under what general conditions is it ...
Retracted on December 2, 2020: On the Value of Look-Ahead in Competitive Online Convex Optimization
RETRACTION NOTICE: "On the Value of Look-Ahead in Competitive Online Convex Optimization," by Shi et al., ACM SIGMETRICS Performance Evaluation Review, Volume 47, Issue 1, Article No. 22, has been retracted at the request of the authors because they ...
On the Value of Look-Ahead in Competitive Online Convex Optimization
SIGMETRICS '19: Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer SystemsAlthough using look-ahead information is known to improve the competitive ratios of online convex optimization (OCO) problems with switching costs, the competitive ratios obtained from existing results often depend on the cost coefficients of the ...






Comments