Online Learning of Competitive Equilibria in Exchange Economies

The sharing of scarce resources among multiple rational agents is one of the classical problems in economics. In exchange economies, which are used to model such situations, agents begin with an initial endowment of resources and exchange them in a way that is mutually beneficial until they reach a competitive equilibrium (CE). CE allocations are Pareto efficient and fair. Consequently, they are used widely in designing mechanisms for fair division. However, computing CEs requires the knowledge of agent preferences which are unknown in several applications of interest. In this work, we explore a new online learning mechanism, which, on each round, allocates resources to the agents and collects stochastic feedback on their experience in using that allocation. Its goal is to learn the agent utilities via this feedback and imitate the allocations at a CE in the long run. We quantify CE behavior via two losses and propose a randomized algorithm which achieves Õ( √ T ) loss after T rounds under both criteria. Empirically, we demonstrate the effectiveness of this mechanism through numerical simulations.

[1]  Milton Abramowitz,et al.  Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables , 1964 .

[2]  Carlo Curino,et al.  Apache Hadoop YARN: yet another resource negotiator , 2013, SoCC.

[3]  Kirthevasan Kandasamy,et al.  RubberBand: cloud-based hyperparameter tuning , 2021, EuroSys.

[4]  John N. Tsitsiklis,et al.  Linearly Parameterized Bandits , 2008, Math. Oper. Res..

[5]  Ilya Segal,et al.  An Efficient Dynamic Mechanism , 2013 .

[6]  Jie Zhang,et al.  Task Division for Team Success in Crowdsourcing Contests: Resource Allocation and Alignment Effects , 2015, J. Manag. Inf. Syst..

[7]  Bo Li,et al.  Scheduling jobs across geo-distributed datacenters with max-min fairness , 2017, IEEE INFOCOM 2017 - IEEE Conference on Computer Communications.

[8]  Christina Delimitrou,et al.  Paragon: QoS-aware scheduling for heterogeneous datacenters , 2013, ASPLOS '13.

[9]  Lihong Li,et al.  Provable Optimal Algorithms for Generalized Linear Contextual Bandits , 2017, ArXiv.

[10]  Shipra Agrawal,et al.  Analysis of Thompson Sampling for the Multi-armed Bandit Problem , 2011, COLT.

[11]  Rémi Munos,et al.  Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis , 2012, ALT.

[12]  Krzysztof Rzadca,et al.  Autopilot: workload autoscaling at Google , 2020, EuroSys.

[13]  Michael I. Jordan,et al.  Mechanism Design with Bandit Feedback , 2020, ArXiv.

[14]  Kani Chen,et al.  Strong consistency of maximum quasi-likelihood estimators in generalized linear models with fixed and adaptive designs , 1999 .

[15]  Andreas Krause,et al.  Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features , 2018, NeurIPS.

[16]  Aurélien Garivier,et al.  Parametric Bandits: The Generalized Linear Case , 2010, NIPS.

[17]  H. Varian Equity, Envy and Efficiency , 1974 .

[18]  W. R. Thompson ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES , 1933 .

[19]  G. Debreu Existence of competitive equilibrium , 1982 .

[20]  Benjamin C. Lee,et al.  Amdahl's Law in the Datacenter Era: A Market for Fair Processor Allocation , 2018, 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA).

[21]  Nathan Linial,et al.  No justified complaints: on fair sharing of multiple resources , 2011, ITCS '12.

[22]  Pamela C. Cosman,et al.  Competitive Equilibrium Bitrate Allocation for Multiple Video Streams , 2010, IEEE Transactions on Image Processing.

[23]  Benjamin Hindman,et al.  Dominant Resource Fairness: Fair Allocation of Multiple Resource Types , 2011, NSDI.

[24]  Noam Nisan,et al.  Fair allocation without trade , 2012, AAMAS.

[25]  Scott Shenker,et al.  Choosy: max-min fair sharing for datacenter jobs with constraints , 2013, EuroSys '13.

[26]  Tan N. Le,et al.  AlloX: compute allocation in hybrid clusters , 2020, EuroSys.

[27]  Charles H. Kriebel,et al.  Asymmetric Information, Incentives and Intrafirm Resource Allocation , 1982 .

[28]  Thomas P. Hayes,et al.  Stochastic Linear Optimization under Bandit Feedback , 2008, COLT.

[29]  Randy H. Katz,et al.  Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center , 2011, NSDI.

[30]  Moshe Babaioff,et al.  Multi-parameter mechanisms with implicit payment computation , 2013, EC '13.

[31]  Albert Y. Zomaya,et al.  A survey on resource allocation in high performance distributed computing systems , 2013, Parallel Comput..

[32]  Shyam Sunder,et al.  Learning Competitive Equilibrium , 2008 .

[33]  Li Zhang,et al.  Proportional response dynamics in the Fisher market , 2009, Theor. Comput. Sci..

[34]  Judd B. Kessler,et al.  Course Match: A Large-Scale Implementation of Approximate Competitive Equilibrium from Equal Incomes for Combinatorial Allocation , 2015, Oper. Res..

[35]  Haipeng Luo,et al.  Oracle-Efficient Online Learning and Auction Design , 2016, 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS).

[36]  Martin J. Wainwright,et al.  High-Dimensional Statistics , 2019 .

[37]  Peter Auer,et al.  Using Confidence Bounds for Exploitation-Exploration Trade-offs , 2003, J. Mach. Learn. Res..

[38]  Moshe Babaioff,et al.  Fair Allocation through Competitive Equilibrium from Generic Incomes , 2019, FAT.

[39]  Ohad Shamir,et al.  On the Complexity of Bandit Linear Optimization , 2014, COLT.

[40]  Moshe Babaioff,et al.  Competitive Equilibria with Indivisible Goods and Generic Budgets , 2017, Math. Oper. Res..

[41]  Ira Horowitz,et al.  Theory of the Firm: Resource Allocation in a Market Economy. , 1965 .

[42]  Sham M. Kakade,et al.  An Optimal Dynamic Mechanism for Multi-Armed Bandit Processes , 2010, ArXiv.

[43]  Gene M. Amdahl,et al.  Computer Architecture and Amdahl's Law , 2007, Computer.

[44]  Li Zhang,et al.  Tycoon: An implementation of a distributed, market-based resource allocation system , 2004, Multiagent Grid Syst..

[45]  Richard Wolski,et al.  Analyzing Market-Based Resource Allocation Strategies for the Computational Grid , 2001, Int. J. High Perform. Comput. Appl..

[46]  Jin Li,et al.  Egalitarian division under Leontief Preferences , 2013 .

[47]  Andrew V. Goldberg,et al.  Quincy: fair scheduling for distributed computing clusters , 2009, SOSP '09.

[48]  Michael I. Jordan,et al.  Online Learning Demands in Max-min Fairness , 2020, ArXiv.

[49]  Ion Stoica,et al.  Ernest: Efficient Performance Prediction for Large-Scale Advanced Analytics , 2016, NSDI.

[50]  Maria-Florina Balcan,et al.  Sample Complexity of Automated Mechanism Design , 2016, NIPS.