Project Grant 2312753
Award Date
6/1/23
Completion Date
5/31/26
Dollars Obligated
$300K
Federal Agency
Division of Computing and Communication Foundations
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Princeton, NJ 08544, USA
Similar Awards
The Regents of the University of Michigan will use a $299,999 National Science Foundation project grant to research designing Plotkin transform codes via machine learning. Under the grant's three-year period of performance from June 2023 to May 2026, the University will investigate a family of codes called Plotkin transform codes, which include Reed-Muller and Polar codes. The researchers will exploit the Plotkin transform code framework to explore underlying design structures that enable good...
This $196,176 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program will support collaborative research to apply deep learning techniques to the design of new encoding and decoding methods for physical layer communication. The researchers at Princeton University aim to use deep learning tools to generate a new family of codes naturally built for finite block lengths, addressing a longstanding challenge in information theory. In parallel,...
The Trustees of Princeton University was awarded a $150,000 Project Grant from the National Science Foundation Division of Computing and Communication Foundations. The grant supports the collaborative research project "Foundations of Deep Learning: Theory, Robustness, and the Brain?" taking place from December 2021 through November 2024 in Princeton, New Jersey. The grant is part of the NSF's Mathematical and Physical Sciences program (CFDA 47.049), which aims to promote progress in...
This three-year $800,000 project grant from the National Science Foundation's Computer and Information Science and Engineering program aims to advance understanding of large language models through mathematical and conceptual analysis. The Trustees of Princeton University will receive funding to develop simplified generative text models, analyze how language models are trained on such generated texts, examine why learned models can perform downstream tasks, and design new adaptation methods with...
This three-year, $250,000 project grant from the National Science Foundation's Computer and Information Science and Engineering program will support research at Harvard University on approximate coded computing. The research aims to develop new theoretical frameworks and techniques to accelerate distributed machine learning computations, ensure accuracy in the presence of hardware errors and faults, and enable differentially private computations through controlled redundancy. Key products will...
This National Science Foundation project grant of $500,000 supports the development of new algorithms and techniques for graph-based error-correcting codes. Awarded under the Computer and Information Science and Engineering program (CFDA 47.070), the grant provides funding from March 2022 through February 2025 to Stanford University. The project aims to advance the fields of list decoding and local decoding of graph-based codes. Researchers will work to achieve linear-time capacity-achieving...
The National Science Foundation awarded a $600,000 Project Grant to Princeton University under the Computer and Information Science and Engineering program (CFDA 47.070). The grant will support research toward developing a mathematical foundation for deep reinforcement learning over the period from October 1, 2022 to September 30, 2026. Specifically, the project aims to bridge current gaps in theoretical reinforcement learning and deep neural networks by investigating guarantees achievable by...
The National Science Foundation awarded a $266,772 Project Grant to the Regents of the University of Michigan under the Computer and Information Science and Engineering program (CFDA 47.070). The five-year award beginning September 1, 2023 will support research investigating the connections between coding theory, specifically list decoding of error-correcting codes, and pseudorandomness theory. The investigator aims to advance the theoretical understanding of fundamental notions like...
The National Science Foundation Division of Computing and Communication Foundations awarded a $500,000 Project Grant to Princeton University from January 1, 2022 to December 31, 2024 to support collaborative research on probabilistic, geometric, and topological analysis of neural networks. This award falls under the Mathematical and Physical Sciences program (CFDA 47.049), which aims to strengthen the Nation's scientific enterprise through advancing knowledge and understanding of major problems....
The Trustees of Princeton University was awarded a $1,200,000 Project Grant from the National Science Foundation Division of Information and Intelligent Systems. The grant supports research titled "MEDIUM: PROVABLE REINFORCEMENT LEARNING WITH FUNCTION APPROXIMATION AND NEURAL NETWORKS" from October 1, 2021 to September 30, 2024. The research aims to advance development of reinforcement learning techniques using function approximation and neural networks under the NSF's Computer and...