Project Grant N000142512251

This Project Grant from the National Science Foundation's $250,000 Computer and Information Science and Engineering program will support research at Purdue University from March 2022 to February 2025. The research aims to develop novel strategies for sequential decision-making under uncertainty with submodular rewards. Specifically, the university researchers will create provably good algorithms for multi-armed bandit problems involving combinatorial action spaces and submodular rewards,...

This Project Grant award from the National Science Foundation (NSF) Office of Advanced Cyberinfrastructure under the CFDA program "Computer and Information Science and Engineering" provides $150,000 to Duke University to conduct collaborative research on developing efficient and provable algorithms for approximate sampling-based exploration strategies in sequential decision-making problems. The key objectives are to unify exploration strategies across different applications like...

This $474,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop a suite of neural network algorithms that can efficiently train deep learning models using limited or "bandit" feedback. The project will focus on three key research thrusts: Advancing bandit learning methods for more complex neural network architectures and establishing new deep learning theory under bandit...

This Project Grant from the National Science Foundation Division of Computing and Communication Foundations, under the Computer and Information Science and Engineering program (CFDA 47.070), provides $250,000 to Iowa State University to support research and education activities from March 1, 2022 to February 28, 2025. The award will fund the development of novel strategies for solving sequential decision-making problems under uncertainty with submodular rewards. Researchers will create...

This Project Grant from the National Science Foundation's Computer and Information Science and Engineering program provides $600,000 to the University of Michigan to develop a new analytical method for analyzing large-scale stochastic systems from July 2022 to June 2025. The method aims to obtain non-asymptotic performance bounds for stochastic networks and systems using Lyapunov drift analysis combined with ideas from Stein's method, dimensionality reduction, and reproducing kernel Hilbert...

This National Science Foundation (NSF) Office of Advanced Cyberinfrastructure grant, awarded under the Computer and Information Science and Engineering program (CFDA 47.070), provides $150,000 from October 1, 2023 to September 30, 2026 to the University of California, Los Angeles (UCLA) to conduct collaborative research on developing efficient and provably effective exploration strategies for sequential decision-making problems in artificial intelligence applications. The key products and...

This National Science Foundation project grant of $146,801 will support research into new approaches for modeling games of incomplete information from July 2022 through June 2025. Funded under the Social, Behavioral, and Economic Sciences program, the research aims to develop robust predictive tools for strategic situations where outcomes depend on unobserved states and players receive private signals. Specifically, the grant will further generalized solution concepts that characterize...

This three-year National Science Foundation project grant of $301,244 will fund research into improving reinforcement learning methods through analyzing their connection to gradient descent. The grant was awarded by the NSF Division of Computing and Communication Foundations under the Computer and Information Science and Engineering program. The grantee, Trustees of Boston University, will explore a novel approach to analyzing and designing convergent reinforcement learning algorithms based...

Purdue University was awarded a $450,000 project grant from the National Science Foundation's Social, Behavioral, and Economic Sciences program (CFDA 47.075) to advance trustworthy reinforcement learning techniques for online decision making. The three-year award beginning August 15, 2022 will support research into robustness, fairness, causality and explainability in dynamic pricing, dynamic assortment selection and two-sided market matching. The University will develop new theoretical...

The Carnegie Mellon University was awarded a $300,000 Project Grant from the National Science Foundation Division of Mathematical Sciences to support research focusing on long-term investing in high-dimensional open markets. The three-year award, made on August 1, 2022, will fund analysis of explicit, tractable models of open markets where the set of available assets can vary over time. In particular, the research will advance understanding of recently developed hybrid and rank Jacobi models,...