Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
Quantifying the cost of learning in queueing systems
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 285, Pages 6532–6544Queueing systems are widely applicable stochastic models with use cases in communication networks, healthcare, service systems, etc. Although their optimal control has been extensively studied, most existing approaches assume perfect knowledge of the ...
- research-articleNovember 2023
Static Pricing for Multi-unit Prophet Inequalities
Characterizing the Efficiency of Static Pricing Schemes as a Function of the Supply
The problem of selling a supply of k units to a stream of customers constitutes one of the cornerstones in revenue management. Static pricing schemes (that output the same ...
We study a pricing problem where a seller has k identical copies of a product, buyers arrive sequentially, and the seller prices the items aiming to maximize social welfare. When k = 1, this is the so-called prophet inequality problem for which there is a ...
- research-articleSeptember 2023
Efficient Decentralized Multi-agent Learning in Asymmetric Bipartite Queueing Systems
New Algorithm Enables Efficient Decentralized Learning in Bipartite Queueing Systems
Bipartite queueing systems, where agents with individual job queues request service from a pool of heterogeneous servers, are standard models for service applications like ...
We study decentralized multiagent learning in bipartite queueing systems, a standard model for service systems. In particular, N agents request service from K servers in a fully decentralized way, that is, by running the same algorithm without ...
- extended-abstractJuly 2023
Group fairness in dynamic refugee assignment
EC '23: Proceedings of the 24th ACM Conference on Economics and ComputationPage 701https://doi.org/10.1145/3580507.3597758Ensuring that refugees and asylum seekers thrive (e.g., find employment) in their host countries is a profound humanitarian goal, and a primary driver of employment is the geographic location to which the refugee or asylum seeker is assigned. In the ...
- research-articleJuly 2023
Contextual Search in the Presence of Adversarial Corruptions
Contextual search is a generalization of binary search, which captures settings such as feature-based dynamic pricing. In this paradigm, a decision maker repeatedly interacts with a set of agents; in the pricing example, the decision maker first observes ...
We study contextual search, a generalization of binary search in higher dimensions, which captures settings such as feature-based dynamic pricing. Standard formulations of this problem assume that agents act in accordance with a specific homogeneous ...
- research-articleAugust 2022
Small-Loss Bounds for Online Learning with Partial Information
Mathematics of Operations Research (MOOR), Volume 47, Issue 3Pages 2186–2218https://doi.org/10.1287/moor.2021.1204We consider the problem of adversarial (nonstochastic) online learning with partial-information feedback, in which, at each round, a decision maker selects an action from a finite set of alternatives. We develop a black-box approach for such problems in ...
- extended-abstractJuly 2022
Learning in Stackelberg Games with Non-myopic Agents
EC '22: Proceedings of the 23rd ACM Conference on Economics and ComputationPages 917–918https://doi.org/10.1145/3490486.3538308Stackelberg games are a canonical model for strategic principal-agent interactions. Consider, for instance, a defense system that distributes its security resources across high-risk targets prior to attacks being executed; or a tax policymaker who sets ...
- research-articleMay 2022
Pricing and Optimization in Shared Vehicle Systems: An Approximation Framework
The optimal management of shared vehicle systems, such as bike-, scooter-, car-, or ride-sharing, is more challenging compared with traditional resource allocation settings because of the presence of spatial externalities—changes in the demand/supply at ...
Optimizing shared vehicle systems (bike-/scooter-/car-/ride-sharing) are more challenging compared with traditional resource allocation settings because of the presence of complex network externalities—changes in the demand/supply at any location affect ...
- research-articleJune 2024
Bayesian decision-making under misspecifed priors with applications to meta-learning
- Max Simchowitz,
- Christopher Tosh,
- Akshay Krishnamurthy,
- Daniel Hsu,
- Thodoris Lykouris,
- Miroslav Dudík,
- Robert Schapire
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsArticle No.: 2020, Pages 26382–26394Thompson sampling and other Bayesian sequential decision-making algorithms are among the most popular approaches to tackle explore/exploit trade-offs in (contextual) bandits. The choice of prior in these algorithms offers fexibility to encode domain ...
- research-articleJuly 2021
Competitive Caching with Machine Learned Advice
Journal of the ACM (JACM), Volume 68, Issue 4Article No.: 24, Pages 1–25https://doi.org/10.1145/3447579Traditional online algorithms encapsulate decision making under uncertainty, and give ways to hedge against all possible future events, while guaranteeing a nearly optimal solution, as compared to an offline optimum. On the other hand, machine learning ...
- research-articleJune 2021
Contextual search in the presence of irrational agents
STOC 2021: Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of ComputingPages 910–918https://doi.org/10.1145/3406325.3451120We study contextual search, a generalization of binary search in higher dimensions, which captures settings such as feature-based dynamic pricing. Standard game-theoretic formulations of this problem assume that agents act in accordance with a specific ...
- research-articleDecember 2020
Constrained episodic reinforcement learning in concave-convex and knapsack settings
- Kianté Brantley,
- Miroslav Dudík,
- Thodoris Lykouris,
- Sobhan Miryoosefi,
- Max Simchowitz,
- Aleksandrs Slivkins,
- Wen Sun
NIPS '20: Proceedings of the 34th International Conference on Neural Information Processing SystemsArticle No.: 1369, Pages 16315–16326We propose an algorithm for tabular episodic reinforcement learning (RL) with constraints. We provide a modular analysis with strong theoretical guarantees for two general settings. First is the convex-concave setting: maximization of a concave reward ...
- research-articleJuly 2020
Bandits with adversarial scaling
ICML'20: Proceedings of the 37th International Conference on Machine LearningArticle No.: 604, Pages 6511–6521We study adversarial scaling, a multi-armed bandit model where rewards have a stochastic and an adversarial component. Our model captures display advertising where the click-through-rate can be decomposed to a (fixed across time) armquality component and ...
- ArticleDecember 2018
On preserving non-discrimination when combining expert advice
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsPages 8386–8397We study the interplay between sequential decision making and avoiding discrimination against protected groups, when examples arrive online and do not follow distributional assumptions. We consider the most basic extension of classical online learning: ...
- research-articleJune 2018
Stochastic bandits robust to adversarial corruptions
STOC 2018: Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of ComputingPages 114–122https://doi.org/10.1145/3188745.3188918We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm, e.g., click ...
- abstractJune 2017
Pricing and Optimization in Shared Vehicle Systems: An Approximation Framework
EC '17: Proceedings of the 2017 ACM Conference on Economics and ComputationPage 517https://doi.org/10.1145/3033274.3085099Optimizing shared vehicle systems (bike-sharing/car-sharing/ride-sharing) is more challenging compared to traditional resource allocation settings due to the presence of complex network externalities. In particular, changes in the demand/supply at any ...
- ArticleDecember 2016
Learning in games: robustness of fast convergence
NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing SystemsPages 4734–4742We show that learning algorithms satisfying a low approximate regret property experience fast convergence to approximate optimality in a large class of repeated games. Our property, which simply requires that each learner has small regret compared to a (...
- research-articleJanuary 2016
Learning and efficiency in games with dynamic population
SODA '16: Proceedings of the twenty-seventh annual ACM-SIAM symposium on Discrete algorithmsPages 120–129We study the quality of outcomes in repeated games when the population of players is dynamically changing, and where participants use learning algorithms to adapt to the dynamic environment. Price of anarchy has originally been introduced to study the ...