Project Grant 2301050
Award Date
10/1/22
Completion Date
6/30/23
Dollars Obligated
$260K
Federal Agency
Division of Mathematical Sciences
Federal Grant Program
47.049
Assistance Type
Project Grant
Place of Performance
Cambridge, MA 02139, USA
Similar Awards
This Project Grant award of $600,000 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support research at the Massachusetts Institute of Technology (MIT) from October 1, 2024 to September 30, 2027. The project aims to design better algorithms for learning problems in linear dynamical systems, graphical models, and hidden Markov models, with the goal of bridging the gap between the tools and perspectives of classic...
This $375,000 Project Grant award, provided by the National Science Foundation (NSF) under the Mathematical and Physical Sciences (CFDA 47.049) federal grant program, aims to advance the understanding of statistical analysis within a broader environment involving multiple stakeholders with different incentives and information asymmetry. The project, led by the Massachusetts Institute of Technology (MIT), seeks to develop statistical protocols that are robust to the strategic behavior of...
The Massachusetts Institute of Technology (MIT) received a $330,000 Project Grant award from the National Science Foundation (NSF) under the Mathematical and Physical Sciences program. The grant supports research from 2023 to 2026 on non-parametric estimation techniques to address challenges with covariate shift in machine learning models. Specifically, MIT researchers will characterize fundamental limits of estimation with covariate shift, develop efficient algorithms that achieve these limits,...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Project Grant award of $122,000, awarded to the Massachusetts Institute of Technology (MIT) from June 1, 2025 to May 31, 2030, supports fundamental research to develop new mathematical tools for analyzing sampling algorithms used ubiquitously across fields like materials science, statistical physics, and artificial intelligence. The project aims to tackle three foundational problems in theoretical...
The Massachusetts Institute of Technology (MIT) received a $531,494 Project Grant award from the National Science Foundation Division of Computing and Communication Foundations on May 1, 2023 to complete work by April 30, 2026. Under this award, MIT will conduct research investigating low-degree methods for optimization in random structures and their potential and limitations. Specifically, MIT aims to verify if low-degree method-based algorithms can achieve state-of-the-art performance across a...
The National Science Foundation (NSF) awarded a $395,910 Project Grant to the Massachusetts Institute of Technology (MIT) under the Mathematical and Physical Sciences (MPS) program (CFDA 47.049) to fund research on statistical and computational thresholds in spin glasses and graph inference problems. The 3-year project, which will run from September 1, 2024 to August 31, 2027, aims to develop new methods for analyzing long-range dependencies and characterizing the typical behaviors of large...
This $600,000 Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CFDA 47.070) program supports fundamental and applied research to develop mathematical foundations for leveraging graph data in machine learning tasks. The key objectives are to: Characterize how the geometry of the underlying latent space affects structural and combinatorial properties of graphs, Derive optimal algorithms for recovering latent feature vectors from...
The Massachusetts Institute of Technology (MIT) received a three-year $600,000 Project Grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering program (CFDA 47.070) to develop algorithms that leverage structural properties in distribution testing. MIT will extend the reach of distribution testing through more efficient solutions that capitalize on known data structures. The university will also design sample-efficient methods to ascertain if data...
This $272,750 federal Project Grant award, funded by the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (CFDA 47.075) program, supports research conducted by the Massachusetts Institute of Technology (MIT) focused on understanding human decision-making, social interactions, and behavioral patterns. The research explores areas such as the implications of limited memory on economic behavior, the dynamics of sharing information on social media, and the influence of...
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...