Gautam Goel
Abstract
We study smoothed online convex optimization, a version of online convex optimization where the learner incurs a penalty for changing her actions between rounds. Given a Ω(pd) lower bound on the competitive ratio of any online algorithm, where d is the dimension of the action space, we ask under what conditions this bound can be beaten. We introduce a novel algorithmic framework for this problem, Online Balanced Descent (OBD), which works by iteratively projecting the previous point onto a carefully chosen level set of the current cost function so as to balance the switching costs and hitting costs. We demonstrate the generality of the OBD framework by showing how, with different choices of "balance," OBD can improve upon state-of-theart performance guarantees for both competitive ratio and regret; in particular, OBD is the first algorithm to achieve a dimension-free competitive ratio, 3 + O(1/α), for locally polyhedral costs, where - measures the "steepness" of the costs. We also prove bounds on the dynamic regret of OBD when the balance is performed in the dual space that are dimension-free and imply that OBD has sublinear static regret.
- R. Agrawal, M. Hegde, and D. Teneketzis. Multi-armed bandit problems with multiple plays and switching cost. Stochastics and Stochastic Reports, 29(4):437--459, 1990.Google Scholar
Cross Ref
- L. Andrew, S. Barman, K. Ligett, M. Lin, A. Meyerson, A. Roytman, and A. Wierman. A tale of two metrics: Simultaneous bounds on competitiveness and regret. In Conference on Learning Theory, pages 741--763, 2013.Google ScholarDigital Library
- A. Antoniadis, N. Barcelo, M. Nugent, K. Pruhs, K. Schewior, and M. Scquizzato. Chasing convex bodies and functions. In Latin American Symposium on Theoretical Informatics, pages 68--81. Springer, 2016.Google ScholarCross Ref
- M. Badiei, N. Li, and A. Wierman. Online convex optimization with ramp constraints. In IEEE Conference on Decision and Control, pages 6730--6736, 2015.Google ScholarCross Ref
- N. Bansal, A. Gupta, R. Krishnaswamy, K. Pruhs, K. Schewior, and C. Stein. A 2-competitive algorithm for online convex optimization with switching costs. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques, pages 96--109, 2015.Google Scholar
- A. Borodin and R. El-Yaniv. Online computation and competitive analysis. Cambridge University Press, 2005. Google ScholarDigital Library
- A. Borodin, N. Linial, and M. E. Saks. An optimal on-line algorithm for metrical task system. J. ACM, 39(4):745--763, Oct. 1992. Google ScholarDigital Library
- N. Chen, A. Agarwal, A. Wierman, S. Barman, and L. L. Andrew. Online convex optimization using predictions. In ACM SIGMETRICS Performance Evaluation Review, volume 43, pages 191--204. ACM, 2015. Google ScholarDigital Library
- N. Chen, J. Comden, Z. Liu, A. Gandhi, and A. Wierman. Using predictions in online optimization: Looking forward with an eye on the past. SIGMETRICS Perform. Eval. Rev., 44(1):193--206, June 2016. Google ScholarDigital Library
- N. Chen, G. Goel, and A. Wierman. Smoothed online convex optimization in high dimensions via online balanced descent. CoRR, abs/1803.10366, 2018.Google Scholar
- J. Friedman and N. Linial. On convex body chasing. Discrete & Computational Geometry, 9(3):293--321, Mar 1993. Google ScholarDigital Library
- G. Goel, N. Chen, and A. Wierman. Thinking fast and slow: Optimization decomposition across timescales. CoRR, abs/1704.07785, 2017.Google Scholar
- S. Guha and K. Munagala. Multi-armed bandits with metric switching costs. In International Colloquium on Automata, Languages, and Programming, pages 496--507. Springer, 2009. Google ScholarDigital Library
- V. Joseph and G. de Veciana. Jointly optimizing multi-user rate adaptation for video transport over wireless systems: Mean-fairness-variability tradeo's. In IEEE INFOCOM, pages 567--575, 2012.Google ScholarCross Ref
- S.-J. Kim and G. B. Giannakis. Real-time electricity pricing for demand response using online convex optimization. In IEEE Innovative Smart Grid Tech., pages 1--5, 2014.Google ScholarCross Ref
- T. Kim, Y. Yue, S. Taylor, and I. Matthews. A decision tree framework for spatiotemporal sequence prediction. In ACM International Conference on Knowledge Discovery and Data Mining, pages 577--586, 2015. Google ScholarDigital Library
- T. Koren, R. Livni, and Y. Mansour. Multi-armed bandits with metric movement costs. In Advances in Neural Information Processing Systems, pages 4122--4131, 2017. Google ScholarDigital Library
- Y. Li, G. Qu, and N. Li. Online optimization with predictions and switching costs: Fast algorithms and the fundamental limit. CoRR, abs/1801.07780, 2018.Google Scholar
- M. Lin, Z. Liu, A. Wierman, and L. L. Andrew. Online algorithms for geographical load balancing. In IEEE Green Computing Conference, pages 1--10, 2012. Google ScholarDigital Library
- M. Lin, A. Wierman, L. L. H. Andrew, and T. Eno. Dynamic right-sizing for power-proportional data centers. In IEEE INFOCOM, pages 1098--1106, 2011.Google ScholarCross Ref
- T. Lu, M. Chen, and L. L. Andrew. Simple and effective dynamic provisioning for power-proportional data centers. IEEE Transactions on Parallel and Distributed Systems, 24(6):1161--1171, 2013. Google ScholarDigital Library
- K. Pruhs. Errata. http://people.cs.pitt.edu/~kirk/Errata.html.Google Scholar
- H. Wang, J. Huang, X. Lin, and H. Mohsenian-Rad. Exploring smart grid and data center interactions for electric power load balancing. ACM SIGMETRICS Performance Evaluation Review, 41(3):89--94, 2014. Google ScholarDigital Library
- F. Zanini, D. Atienza, L. Benini, and G. De Micheli. Multicore thermal management with model predictive control. In IEEE. European Conf. Circuit Theory and Design, pages 711--714, 2009.Google ScholarCross Ref
- F. Zanini, D. Atienza, G. De Micheli, and S. P. Boyd. Online convex optimization-based algorithm for thermal management of MPSoCs. In The Great lakes symposium on VLSI, pages 203--208, 2010. Google ScholarDigital Library
Index Terms
- Smoothed Online Convex Optimization via Online Balanced Descent
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 ...
An Online Algorithm for Smoothed Online Convex Optimization
We consider Online Convex Optimization (OCO) in the setting where the costs are m-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) ...
Beyond online balanced descent: an optimal algorithm for smoothed online optimization
NIPS'19: Proceedings of the 33rd International Conference on Neural Information Processing SystemsWe study online convex optimization in a setting where the learner seeks to minimize the sum of a per-round hitting cost and a movement cost which is incurred when changing decisions between rounds. We prove a new lower bound on the competitive ratio of ...
Comments