Project Grant FA95502410092

This three-year Project Grant from the National Science Foundation's Division of Computing and Communication Foundations under the Computer and Information Science and Engineering program will support the development of new optimization approaches for machine learning problems. The $600,000 award to the University of Wisconsin-Madison beginning October 1, 2022 will advance optimization algorithms and analysis techniques for convex-concave minimax problems incorporating sparsity or regularity....

This Project Grant from the National Science Foundation's Mathematical and Physical Sciences program provides $171,089 to Old Dominion University Research Foundation for collaborative research developing computationally efficient methods for non-smooth and non-convex optimization by exploring sparsity structures in large data sets. The research aims to address critical issues in non-smooth, non-convex optimization arising from sparse modeling of data used in machine learning and sparse...

This two-year, $251,672 project grant from the National Science Foundation's Computer and Information Science and Engineering program (CFDA 47.070) will support research into non-smooth and non-Lipschitz Riemannian optimization methods. The grantee, Rice University, will study algorithmic approaches such as the manifold alternating direction method of multipliers and inertial manifold proximal gradient method to develop new tools for solving important classes of non-convex optimization...

This National Science Foundation (NSF) Engineering program (CFDA 47.041) grant award of $440,320 to the Regents of the University of Michigan aims to develop innovative online convex optimization methods to improve the performance of high-precision control systems used in a variety of engineering applications. The research is divided into three thrusts: (1) establishing fundamental performance limits for robust disturbance rejection, (2) creating new versions of recursive least squares...

The National Science Foundation awarded a $250,000 Project Grant to the Texas A&M Engineering Experiment Station to support research titled "Collaborative Research: Consensus and Distributed Optimization in Non-Convex Environments with Applications to Networked Machine Learning." The award is part of the NSF Engineering program (CFDA 47.041), which aims to foster innovation and excellence in engineering research. Under the three-year award concluding in July 2026, the Texas A&M...

This National Science Foundation project grant of $362,015 supports research into developing more fine-grained algorithms under the Computer and Information Science and Engineering program. The University of California, San Diego will conduct this research from November 2021 to January 2023. Specifically, the awardee will build a unified theory of designing fast approximation algorithms and study their fine-grained computational hardness. They will develop systematic techniques emphasizing...

This National Science Foundation project grant of $250,000 will fund research at Rensselaer Polytechnic Institute from July 2022 to June 2025 under the Mathematical and Physical Sciences program (CFDA 47.049). The grant supports the development of accelerated distributed stochastic optimization methods and applications in machine learning. Specifically, the grantee will design fast-convergent and communication-efficient optimization algorithms with theoretical guarantees for solving...

This $199,996 project grant awarded by the National Science Foundation (NSF) Engineering program (CFDA 47.041) aims to develop a principled approach to the systematic design of efficient iterative algorithms for a wide variety of data-driven applications. The project at Miami University will leverage tools from both optimization and control theory, including techniques like interpolation, Lyapunov stability, and robust control synthesis, to enable the deployment of specialized and efficient...

This Project Grant from the National Science Foundation's (NSF) Mathematical and Physical Sciences program (CFDA 47.049) provides $227,139 to the University of California, Davis for research related to solving systems of linear inequalities with parameters and developing efficient algorithms for constrained interpolation by smooth functions. Over a three-year period from July 1, 2023 through June 30, 2026, the University will work to develop smooth solutions to systems of linear inequalities and...

This $235,622 National Science Foundation Project Grant under the Mathematical and Physical Sciences program (CFDA 47.049) supports the development of scalable computational methods for large-scale stochastic optimization of partial differential equations with high-dimensional uncertainty. Key products include analysis of the intrinsic low-dimensionality of parameter-to-objective maps for stochastic PDE-constrained optimization problems. Methods to be developed include extension of local...