Group-fair online allocation in continuous time
Article No.: 1153, Pages 13750 - 13761
Abstract
The theory of discrete-time online learning has been successfully applied in many problems that involve sequential decision-making under uncertainty. However, in many applications including contractual hiring in online freelancing platforms and server allocation in cloud computing systems, the outcome of each action is observed only after a random and action-dependent time. Furthermore, as a consequence of certain ethical and economic concerns, the controller may impose deadlines on the completion of each task, and require fairness across different groups in the allocation of total time budget B. In order to address these applications, we consider continuous-time online learning problem with fairness considerations, and present a novel framework based on continuous-time utility maximization. We show that this formulation recovers reward-maximizing, max-min fair and proportionally fair allocation rules across different groups as special cases. We characterize the optimal offline policy, which allocates the total time between different actions in an optimally fair way (as defined by the utility function), and impose deadlines to maximize time-efficiency. In the absence of any statistical knowledge, we propose a novel online learning algorithm based on dual ascent optimization for time averages, and prove that it achieves Õ(B-1/2) regret bound.
Supplementary Material
Supplemental material.
- Download
- 1.24 MB
References
[1]
J. Zhao, T. Wang, M. Yatskar, V. Ordonez, and K.-W. Chang, "Men also like shopping: Reducing gender bias amplification using corpus-level constraints," arXiv preprint arXiv:1707.09457, 2017.
[2]
T. Bolukbasi, K.-W. Chang, J. Y. Zou, V. Saligrama, and A. T. Kalai, "Man is to computer programmer as woman is to homemaker? debiasing word embeddings," in Advances in Neural Information Processing Systems, 2016, pp. 4349-4357.
[3]
A. Caliskan, J. J. Bryson, and A. Narayanan, "Semantics derived automatically from language corpora contain human-like biases," Science, vol. 356, no. 6334, pp. 183-186, 2017.
[4]
K. Lum and W. Isaac, "To predict and serve?" Significance, vol. 13, no. 5, pp. 14-19, 2016.
[5]
A. L. Washington, "How to argue with an algorithm: Lessons from the compas-propublica debate," Colo. Tech. LJ, vol. 17, p. 131, 2018.
[6]
J. Kleinberg, "Inherent trade-offs in algorithmic fairness," in Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems, 2018, pp. 40-40.
[7]
A. Chouldechova, "Fair prediction with disparate impact: A study of bias in recidivism prediction instruments," Big data, vol. 5, no. 2, pp. 153-163, 2017.
[8]
G. Laumeister, "The next big thing in e-commerce: Online labor marketplaces," Forbes (Online), 2014.
[9]
H. Torry, "Coronavirus pandemic deepens labor divide between online, offline workers," Wall Street Journal, 2020.
[10]
A. Teeley, "There are 57 million u.s. independent professionals — upwork wants them all to succeed," Built In Chicago, 2020.
[11]
A. Hannák, C. Wagner, D. Garcia, A. Mislove, M. Strohmaier, and C. Wilson, "Bias in online freelance marketplaces: Evidence from taskrabbit and fiverr," in Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, 2017, pp. 1914-1933.
[12]
R. Srikant and L. Ying, Communication networks: an optimization, control, and stochastic networks perspective. Cambridge University Press, 2013.
[13]
D. Bertsimas, V. F. Farias, and N. Trichakis, "On the efficiency-fairness trade-off," Management Science, vol. 58, no. 12, pp. 2234-2250, 2012.
[14]
K. Jain and V. V. Vazirani, "Eisenberg-gale markets: Algorithms and structural properties," in Proceedings of the thirty-ninth annual ACM symposium on Theory of computing, 2007, pp. 364-373.
[15]
D. P. Palomar and M. Chiang, "A tutorial on decomposition methods for network utility maximization," IEEE Journal on Selected Areas in Communications, vol. 24, no. 8, pp. 1439-1451, 2006.
[16]
A. Eryilmaz and R. Srikant, "Fair resource allocation in wireless networks using queue-length-based scheduling and congestion control," IEEE/ACM transactions on networking, vol. 15, no. 6, pp. 1333-1344, 2007.
[17]
H. J. Kushner and P. A. Whiting, "Convergence of proportional-fair sharing algorithms under general conditions," IEEE Transactions on Wireless Communications, vol. 3, no. 4, pp. 1250-1259, 2004.
[18]
D. Kahneman and R. H. Thaler, "Anomalies: Utility maximization and experienced utility," Journal of economic perspectives, vol. 20, no. 1, pp. 221-234, 2006.
[19]
M. J. Neely, "Dynamic optimization and learning for renewal systems," IEEE Transactions on Automatic Control, vol. 58, no. 1, pp. 32-46, 2012.
[20]
A. Badanidiyuru, R. Kleinberg, and A. Slivkins, "Bandits with knapsacks," Journal of the ACM (JACM), vol. 65, no. 3, pp. 1-55, 2018.
[21]
L. Tran-Thanh, A. Chapman, A. Rogers, and N. R. Jennings, "Knapsack based optimal policies for budget-limited multi-armed bandits," in Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012.
[22]
A. Slivkins, "Introduction to multi-armed bandits," arXiv preprint arXiv:1904.07272, 2019.
[23]
S. Cayci, A. Eryilmaz, and R. Srikant, "Learning to control renewal processes with bandit feedback," Proceedings of the ACM on Measurement and Analysis of Computing Systems, vol. 3, no. 2, pp. 1-32, 2019.
[24]
S. Agrawal and N. R. Devanur, "Bandits with concave rewards and convex knapsacks," in Proceedings of the fifteenth ACM conference on Economics and computation, 2014, pp. 989-1006.
[25]
A. Rosenblat, K. E. Levy, S. Barocas, and T. Hwang, "Discriminating tastes: Customer ratings as vehicles for bias," Available at SSRN 2858946, 2016.
[26]
A. Chakraborty, A. Hannak, A. J. Biega, and K. P. Gummadi, "Fair sharing for sharing economy platforms," 2017.
[27]
M. Harchol-Balter, "Task assignment with unknown duration," in Proceedings 20th IEEE International Conference on Distributed Computing Systems. IEEE, 2000, pp. 214-224.
[28]
R. Motwani, S. Phillips, and E. Torng, "Nonclairvoyant scheduling," Theoretical computer science, vol. 130, no. 1, pp. 17-47, 1994.
[29]
M. Harchol-Balter and A. B. Downey, "Exploiting process lifetime distributions for dynamic load balancing," ACM Transactions on Computer Systems (TOCS), vol. 15, no. 3, pp. 253-285, 1997.
[30]
K. Kim and A. A. Tsiatis, "Study duration for clinical trials with survival response and early stopping rule," Biometrics, pp. 81-92, 1990.
[31]
P. F. Thall, R. Simon, and S. S. Ellenberg, "Two-stage selection and testing designs for comparative clinical trials," Biometrika, vol. 75, no. 2, pp. 303-310, 1988.
[32]
P. R. Jelenković and J. Tan, "Characterizing heavy-tailed distributions induced by retransmissions," Advances in Applied Probability, vol. 45, no. 1, pp. 106-138, 2013.
[33]
C. H. Papadimitriou and J. N. Tsitsiklis, "The complexity of optimal queuing network control," Mathematics of Operations Research, vol. 24, no. 2, pp. 293-305, 1999.
[34]
S. Asmussen, Applied probability and queues. Springer Science & Business Media, 2008, vol. 51.
[35]
M. Neely, Stochastic network optimization with application to communication and queueing systems. Morgan & Claypool Publishers, 2010.
[36]
R. Zabolotnyi, P. Leitner, and S. Dustdar, "Profiling-based task scheduling for factory-worker applications in infrastructure-as-a-service clouds," in 2014 40th EUROMICRO Conference on Software Engineering and Advanced Applications. IEEE, 2014, pp. 119-126.
[37]
J. Kleinberg and M. Raghavan, "Selection problems in the presence of implicit bias," arXiv preprint arXiv:1801.03533, 2018.
[38]
M. Harchol-Balter, "The effect of heavy-tailed job size distributions on computer system design." in Proc. of ASA-IMS Conf. on Applications of Heavy Tailed Distributions in Economics, Engineering and Statistics, 1999.
[39]
W. J. Reed and B. D. Hughes, "From gene families and genera to incomes and internet file sizes: Why power laws are so common in nature," Physical Review E, vol. 66, no. 6, p. 067103, 2002.
[40]
W. Gong, Y. Liu, V. Misra, and D. Towsley, "On the tails of web file size distributions," in Proceedings of the annual allerton conference on communication control and computing, vol. 39, no. 1. The University; 1998, 2001, pp. 192-201.
[41]
J. F. Nash Jr, "The bargaining problem," Econometrica: Journal of the Econometric Society, pp. 155-162, 1950.
[42]
J. W. Pratt, "Risk aversion in the small and in the large," in Uncertainty in Economics. Elsevier, 1978, pp. 59-79.
[43]
N. Nisan and A. Ronen, "Computationally feasible vcg mechanisms," Journal of Artificial Intelligence Research, vol. 29, pp. 19-47, 2007.
[44]
J. Mo and J. Walrand, "Fair end-to-end window-based congestion control," IEEE/ACM Transactions on networking, vol. 8, no. 5, pp. 556-567, 2000.
[45]
F. Kelly, "Charging and rate control for elastic traffic," European transactions on Telecommunications, vol. 8, no. 1, pp. 33-37, 1997.
[46]
L. Tassiulas and A. Ephremides, "Jointly optimal routing and scheduling in packet ratio networks," IEEE Transactions on Information Theory, vol. 38, no. 1, pp. 165-168, 1992.
[47]
L. Tassiulas and A. Ephremides, "Dynamic server allocation to parallel queues with randomly varying connectivity," IEEE Transactions on Information Theory, vol. 39, no. 2, pp. 466-478, 1993.
[48]
M. J. Neely, "A lyapunov optimization approach to repeated stochastic games," in 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton). IEEE, 2013, pp. 1082-1089.
[49]
S. Agrawal and N. Devanur, "Linear contextual bandits with knapsacks," in Advances in Neural Information Processing Systems, 2016, pp. 3450-3458.
[50]
K. A. Sankararaman and A. Slivkins, "Combinatorial semi-bandits with knapsacks," arXiv preprint arXiv:1705.08110, 2017.
[51]
A. Gut, Stopped random walks. Springer, 2009.
[52]
S. Cayci, A. Eryilmaz, and R. Srikant, "Budget-constrained bandits over general cost and reward distributions," arXiv preprint arXiv:2003.00365, 2020.
[53]
M. J. Wainwright, High-dimensional statistics: A non-asymptotic viewpoint. Cambridge University Press, 2019, vol. 48.
[54]
B. Hajek, "Hitting-time and occupation-time bounds implied by drift analysis with applications," Advances in Applied probability, vol. 14, no. 3, pp. 502-525, 1982.
Recommendations
Fair Allocation through Competitive Equilibrium from Generic Incomes
FAT* '19: Proceedings of the Conference on Fairness, Accountability, and TransparencyTwo food banks catering to populations of different sizes with different needs must divide among themselves a donation of food items. What constitutes a "fair" allocation of the items among them?
Competitive equilibrium from equal incomes (CEEI) is a ...
Fair Allocation of Two Types of Chores
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent SystemsWe consider the problem of fair allocation of indivisible chores under additive valuations. We assume that the chores are divided into two types and under this scenario, we present several results. Our first result is a new characterization of Pareto ...
Fair allocation of indivisible goods: Beyond additive valuations
AbstractWe conduct a study on the problem of fair allocation of indivisible goods when maximin share [1] is used as the measure of fairness. Most of the current studies on this notion are limited to the case that the valuations ...
Comments
Information & Contributors
Information
Published In
December 2020
22651 pages
ISBN:9781713829546
- Editors:
- H. Larochelle,
- M. Ranzato,
- R. Hadsell,
- M.F. Balcan,
- H. Lin
Copyright © 2020 Neural Information Processing Systems Foundation, Inc.
Publisher
Curran Associates Inc.
Red Hook, NY, United States
Publication History
Published: 06 December 2020
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 37Total Downloads
- Downloads (Last 12 months)29
- Downloads (Last 6 weeks)6
Reflects downloads up to 13 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in