no code implementations • 3 Apr 2024 • Joo Seung Lee, Malini Mahendra, Anil Aswani
Mechanical ventilation is a critical life-support intervention that uses a machine to deliver controlled air and oxygen to a patient's lungs, assisting or replacing spontaneous breathing.
no code implementations • 6 Feb 2024 • Xin Chen, Sukanya Kudva, Yongzheng Dai, Anil Aswani, Chen Chen
The main challenge with the tensor completion problem is a fundamental tension between computation power and the information-theoretic sample complexity rate.
no code implementations • 13 Aug 2023 • Ilgin Dogan, Zuo-Jun Max Shen, Anil Aswani
On top of the agent's learning, the principal trains a parallel algorithm and faces a trade-off between consistently estimating the agent's unknown rewards and maximizing their own utility by offering adaptive incentives to lead the agent.
no code implementations • 14 Apr 2023 • Ilgin Dogan, Zuo-Jun Max Shen, Anil Aswani
Motivated by a number of real-world applications from domains like healthcare and sustainable transportation, in this paper we study a scenario of repeated principal-agent games within a multi-armed bandit (MAB) framework, where: the principal gives a different incentive for each bandit arm, the agent picks a bandit arm to maximize its own expected reward plus incentive, and the principal observes which arm is chosen and receives a reward (different than that of the agent) for the chosen arm.
1 code implementation • 28 Nov 2022 • Wenhao Pan, Anil Aswani, Chen Chen
A recent approach, based on integer programming, resolves this tension for nonnegative tensor completion.
no code implementations • 27 Nov 2021 • Luca Pion-Tonachini, Kristofer Bouchard, Hector Garcia Martin, Sean Peisert, W. Bradley Holtz, Anil Aswani, Dipankar Dwivedi, Haruko Wainwright, Ghanshyam Pilania, Benjamin Nachman, Babetta L. Marrone, Nicola Falco, Prabhat, Daniel Arnold, Alejandro Wolf-Yadlin, Sarah Powers, Sharlee Climer, Quinn Jackson, Ty Carlson, Michael Sohn, Petrus Zwart, Neeraj Kumar, Amy Justice, Claire Tomlin, Daniel Jacobson, Gos Micklem, Georgios V. Gkoutos, Peter J. Bickel, Jean-Baptiste Cazier, Juliane Müller, Bobbie-Jo Webb-Robertson, Rick Stevens, Mark Anderson, Ken Kreutz-Delgado, Michael W. Mahoney, James B. Brown
We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery.
1 code implementation • 8 Nov 2021 • Caleb Bugg, Chen Chen, Anil Aswani
Unlike matrix completion, tensor completion does not have an algorithm that is known to achieve the information-theoretic sample complexity rate.
no code implementations • 18 Oct 2021 • Rishi Balakrishnan, Stephen Sloan, Anil Aswani
With Internet users constantly leaving a trail of text, whether through blogs, emails, or social media posts, the ability to write and protest anonymously is being eroded because artificial intelligence, when given a sample of previous work, can match text with its author out of hundreds of possible candidates.
no code implementations • 29 Sep 2021 • David C Jenkins, René Arendt Sørensen, Vikramank Singh, Philip Kaminsky, Anil Aswani, Ramakrishna Akella
This paper proposes a novel method based on Deep Reinforcement Learning for developing dynamic scheduling policies through interaction with simulated stochastic manufacturing systems.
no code implementations • 4 Aug 2021 • Ilgin Dogan, Zuo-Jun Max Shen, Anil Aswani
A significant theoretical challenge in the nonlinear setting is that there is no explicit characterization of an optimal controller for a given set of cost and system parameters.
no code implementations • 31 Mar 2020 • Matt Olfat, Stephen Sloan, Pedro Hespanhol, Matt Porter, Ram Vasudevan, Anil Aswani
Attack detection and mitigation strategies for cyberphysical systems (CPS) are an active area of research, and researchers have developed a variety of attack-detection tools such as dynamic watermarking.
1 code implementation • 6 Nov 2018 • Jonathan N. Lee, Michael Laskey, Ajay Kumar Tanwani, Anil Aswani, Ken Goldberg
In this article, we reframe this result using dynamic regret theory from the field of online optimization and show that dynamic regret can be applied to any on-policy algorithm to analyze its convergence and optimality.
no code implementations • 9 Oct 2018 • Matt Olfat, Anil Aswani
We motivate this regularization by a novel generalization bound that shows a tradeoff in classifier accuracy between maximizing its margin and average margin.
2 code implementations • 11 Feb 2018 • Matt Olfat, Anil Aswani
We conclude by showing how our approach can be used to perform a fair (with respect to age) clustering of health data that may be used to set health insurance rates.
no code implementations • 16 Oct 2017 • Matt Olfat, Anil Aswani
Classifiers and rating scores are prone to implicitly codifying biases, which may be present in the training data, against protected classes (i. e., age, gender, or race).
no code implementations • 26 Jul 2017 • Yonatan Mintz, Anil Aswani, Philip Kaminsky, Elena Flowers, Yoshimi Fukuoka
Many settings involve sequential decision-making where a set of actions can be chosen at each time step, each action provides a stochastic reward, and the distribution for the reward of each action is initially unknown.
no code implementations • 1 Dec 2014 • Anil Aswani
Among the consequences is that best rank-1 approximations of positive tensors can be computed in polynomial time.