Search for: All records

We study the query complexity of finding the set of all Nash equilibria\(\mathcal {X}_\ast \times \mathcal {Y}_\ast \)in two-player zero-sum matrix games. Fearnley and Savani [18] showed that for any randomized algorithm, there exists ann×ninput matrix where it needs to queryΩ(n²) entries in expectation to compute asingleNash equilibrium. On the other hand, Bienstock et al. [5] showed that there is a special class of matrices for which one can queryO(n) entries and compute its set of all Nash equilibria. However, these results do not fully characterize the query complexity of finding the set of all Nash equilibria in two-player zero-sum matrix games. In this work, we characterize the query complexity of finding the set of all Nash equilibria\(\mathcal {X}_\ast \times \mathcal {Y}_\ast \)in terms of the number of rowsnof the input matrix\(A \in \mathbb {R}^{n \times n} \), row support size\(k_1 := |\bigcup \limits _{x \in \mathcal {X}_\ast } \text{supp}(x)| \), and column support size\(k_2 := |\bigcup \limits _{y \in \mathcal {Y}_\ast } \text{supp}(y)| \). We design a simple yet non-trivial randomized algorithm that returns the set of all Nash equilibria\(\mathcal {X}_\ast \times \mathcal {Y}_\ast \)by querying at mostO(nk⁵· polylog(n)) entries of the input matrix\(A \in \mathbb {R}^{n \times n} \)in expectation, wherek≔ max{k₁,k₂}. This upper bound is tight up to a factor of poly(k), as we show that for any randomized algorithm, there exists ann×ninput matrix with min {k₁,k₂} = 1, for which it needs to queryΩ(nk) entries in expectation in order to find the set of all Nash equilibria\(\mathcal {X}_\ast \times \mathcal {Y}_\ast \). 

We study the problem of online resource allocation, where customers arrive sequentially, and the seller must irrevocably allocate resources to each incoming customer while also facing a prespecified procurement cost function over the total allocation. The objective is to maximize the reward obtained from fulfilling the customers’ requests sans the cumulative procurement cost. We analyze the competitive ratio of a primal-dual algorithm in this setting and develop an optimization framework for designing a surrogate function for the procurement cost to be used by the algorithm to improve the competitive ratio of the primal-dual algorithm. We use the optimal surrogate function for polynomial procurement cost functions to improve on previous bounds. For general procurement cost functions, our design method uses quasiconvex optimization to find optimal design parameters. We then implement the design techniques and show the improved performance of the algorithm in numerical examples. Finally, we extend the analysis by devising a posted pricing mechanism in which the algorithm does not require the customers’ preferences to be revealed. Funding: M. Fazel’s work was supported in part by the National Science Foundation [Awards 2023166, 2007036, and 1740551]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/ijoo.2021.0012 . 

This paper investigates ML systems serving a group of users, with multiple models/services, each aimed at specializing to a sub-group of users. We consider settings where upon deploying a set of services, users choose the one minimizing their personal losses and the learner iteratively learns by interacting with diverse users. Prior research shows that the outcomes of learning dynamics, which comprise both the services' adjustments and users' service selections, hinge significantly on the initial conditions. However, finding good initial conditions faces two main challenges:(i)\emph {Bandit feedback:} Typically, data on user preferences are not available before deploying services and observing user behavior;(ii)\emph {Suboptimal local solutions:} The total loss landscape (ie, the sum of loss functions across all users and services) is not convex and gradient-based algorithms can get stuck in poor local minima. We address these challenges with a randomized algorithm to adaptively select a minimal set of users for data collection in order to initialize a set of services. Under mild assumptions on the loss functions, we prove that our initialization leads to a total loss within a factor of the\textit {globally optimal total loss, with complete user preference data}, and this factor scales logarithmically in the number of services. This result is a generalization of the well-known k-means++ guarantee to a broad problem class which is also of independent interest. The theory is complemented by experiments on real as well as semi-synthetic datasets.