Online Algorithms with Multiple Predictions
Publication
, Conference
Anand, K; Ge, R; Kumar, A; Panigrahi, D
Published in: Proceedings of Machine Learning Research
January 1, 2022
This paper studies online algorithms augmented with multiple machine-learned predictions. We give a generic algorithmic framework for online covering problems with multiple predictions that obtains an online solution that is competitive against the performance of the best solution obtained from the predictions. Our algorithm incorporates the use of predictions in the classic potential-based analysis of online algorithms. We apply our algorithmic framework to solve classical problems such as online set cover, (weighted) caching, and online facility location in the multiple predictions setting.
Duke Scholars
Published In
Proceedings of Machine Learning Research
EISSN
2640-3498
Publication Date
January 1, 2022
Volume
162
Start / End Page
582 / 598
Citation
APA
Chicago
ICMJE
MLA
NLM
Anand, K., Ge, R., Kumar, A., & Panigrahi, D. (2022). Online Algorithms with Multiple Predictions. In Proceedings of Machine Learning Research (Vol. 162, pp. 582–598).
Anand, K., R. Ge, A. Kumar, and D. Panigrahi. “Online Algorithms with Multiple Predictions.” In Proceedings of Machine Learning Research, 162:582–98, 2022.
Anand K, Ge R, Kumar A, Panigrahi D. Online Algorithms with Multiple Predictions. In: Proceedings of Machine Learning Research. 2022. p. 582–98.
Anand, K., et al. “Online Algorithms with Multiple Predictions.” Proceedings of Machine Learning Research, vol. 162, 2022, pp. 582–98.
Anand K, Ge R, Kumar A, Panigrahi D. Online Algorithms with Multiple Predictions. Proceedings of Machine Learning Research. 2022. p. 582–598.
Published In
Proceedings of Machine Learning Research
EISSN
2640-3498
Publication Date
January 1, 2022
Volume
162
Start / End Page
582 / 598