Marianna Pensky
University of Central Florida, FL·Mathematics & Statistics
Many kinds of data come as networks: brain regions linked by activity, proteins that act on one another, or countries linked by trade. Often there are many related networks at once, such as brain networks from different people or trade networks for different goods.
- Fields
Mathematics & Statistics
Computer Science
Neuroscience
- Topics
network analysis
multilayer networks
multiplex networks
- Grants
- 1 known grant, through Jul 2027
What they work on
- Extend the multiplex Generalized Dot Product Graph model so that groups of network layers can have different underlying structures. This would allow layers to be clustered by condition.
- Develop a signed multiplex GDPG (SGDPG) model for networks whose connections can be positive or negative, to fit a wider range of real networks.
- Design scalable algorithms for fitting multilayer GDPG models. Prove precision guarantees using oracle inequalities and minimax analysis.
- Apply the multilayer GDPG methods to brain networks to describe how networks under different conditions differ from one another.
More about the research
This is called a multilayer network. A key challenge is finding which layers resemble each other and how groups differ, for example how brain networks in a disease differ from healthy ones. This project builds statistical models and theory for that task.
Why it matters
The methods could help brain scientists compare brain networks across conditions. They may give model-based explanations of what makes disease-related brain networks differ from normal ones. The same tools could be used to study protein interaction networks in molecular biology, world trade and financial networks, and social networks with different kinds of ties.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Weijing Tang
Carnegie Mellon University, PA·Mathematics & Statistics
Develop priority-aware rules for valuing training data based on the Shapley value, a game-theory method for fairly splitting credit, that account for originality, provenance and individual risk within a unified axiomatic framework.
Joshua Cape
University of Wisconsin-Madison, WI·Mathematics & Statistics·Early-career
Develop nonparametric spectral clustering and dimension-reduction methods that tolerate messy, mixed data, and apply them to brain network studies of schizophrenia with psychiatry collaborators.
Sreekalyani Bhamidi
University of North Carolina at Chapel Hill, NC·Mathematics & Statistics
Develop statistically principled methods for summarizing, clustering, and extracting principal directions of variation in multilayer network data, using Gaussian process optimal transport and Procrustes metrics on covariance operators expressed via Wasserstein distance.
The school
University of Central Florida: 15 labs on PI Pages, $285M a year on research, 290 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.