Project Grant 2208303

Award Date 7/1/22
Completion Date 6/30/25
Dollars Obligated $164K
Federal Grant Program
47.049
Assistance Type
Project Grant
Place of Performance
Tallahassee, FL 32306, USA
Similar Awards
The National Science Foundation awarded a $152,899 Project Grant to Florida State University (FSU) under the Mathematical and Physical Sciences (CFDA 47.049) program. This grant supports research into stochastic analysis and numerical algorithms for stochastic dynamical systems, and their applications in machine learning and mathematical finance. Key focus areas include hypocoercivity and convergence analysis for degenerate and mean-field stochastic systems, and the study of non-Markovian...
Florida State University was awarded a $159,960 Project Grant from the National Science Foundation on June 1, 2021 to complete work by May 31, 2024. The grant funds a collaborative research project titled "COLLABORATIVE RESEARCH: LANGEVIN MARKOV CHAIN MONTE CARLO METHODS FOR MACHINE LEARNING" under the NSF's Mathematical and Physical Sciences program (CFDA 47.049). The project aims to advance machine learning techniques by developing new Langevin Markov chain Monte Carlo methods. As...
This $293,784 Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences (CFDA 47.049) program supports fundamental and applied research on fluctuating systems, random environments, and stochastic algorithms. The research aims to improve understanding and exploitation of randomness across diverse settings, including materials science, fluid dynamics, and machine learning. Key areas of focus include stochastic homogenization, stochastic partial...
The University of Florida was awarded a $125,701 Project Grant from the National Science Foundation Division of Mathematical Sciences under the Mathematical and Physical Sciences federal grant program (CFDA 47.049). The grant will support the development of a mathematical foundation for novel artificial intelligence learning algorithms with applications to biology and engineering. Specifically, researchers will establish a theoretical framework for the minimax optimization of machine learning...
This Project Grant award of $175,000 from the National Science Foundation's (NSF) Mathematical and Physical Sciences (CFDA 47.049) program supports research to enhance the reliability of data analysis in modern, large-scale datasets, particularly in the era of artificial intelligence. The project develops new statistical and computational methods to address fundamental challenges related to robustness, adaptivity, and structure in modern algorithms and statistical procedures. The research...
The National Science Foundation (NSF) Division of Mathematical Sciences awarded a $331,902 Project Grant to the Trustees of Boston University on August 15, 2023 under the Mathematical and Physical Sciences program (CFDA 47.049). The purpose of this 3-year grant is to develop rigorous mathematical analysis and theory for the training algorithms used in neural network models across various machine learning applications. The research will leverage stochastic analysis and weak convergence theory...
This $125,000 Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences (CFDA 47.049) program will enable the Florida Institute of Technology Inc. (Florida TECH) to utilize advanced machine learning algorithms to efficiently analyze and predict information within high-dimensional data matrices and tensor computations related to state-space dynamical systems. The key objectives are to: (I) utilize machine learning to predict future states of dynamical...
The National Science Foundation (NSF) Division of Mathematical Sciences awarded a $173,740 Project Grant to Florida State University (FSU) Sponsored Research Administration Division to enhance methods for analyzing temporally observed or time-indexed multi-sample data across diverse fields like environmental sciences, epidemiology, and economics. The 3-year grant, starting September 1, 2023, aims to develop innovative statistical techniques to study data that does not fit conventional univariate...
This $300,000 Project Grant from the National Science Foundation's Division of Mathematical Sciences, under the Mathematical and Physical Sciences program (CFDA 47.049), will support the development of next-generation mathematical and algorithmic tools to address two key issues in applying machine learning to statistical modeling of time-evolving complex systems: a shortage of informative training data and the high computational costs of high-dimensional problems. Specifically, the...
This Project Grant award from the National Science Foundation (NSF) Mathematical and Physical Sciences (CFDA 47.049) program provides $216,296 to Louisiana State University (LSU) from September 1, 2024 to August 31, 2027. The project aims to develop novel approaches and underlying theory for online machine learning, with a focus on applications in biomedical research, finance, cybersecurity, and big data. Key aspects include: Exploring the use of partial differential equations and optimal...

The National Science Foundation awarded Florida State University a $163,533 Project Grant under the Mathematical and Physical Sciences program (CFDA 47.049) from July 1, 2022 to June 30, 2025. The award will support research developing a theoretical framework to better understand how heavy-tailed distributions arise in popular machine learning algorithms and how they can explain the success of these algorithms.

The awardee will conduct research obtaining theoretical convergence properties, performance guarantees, and studying additional properties for heavy-tailed stochastic gradient descent and its accelerated momentum-based methods. A novel heavy-tailed adaptive Langevin algorithm and variants will also be developed with theoretical guarantees studied for both sampling and non-convex stochastic optimization. The results are intended to bridge gaps between theory and practice in machine learning and impact developers and practitioners in data science and the mathematics community.

Generated 1/7/24, 6:38 AM