Online Graph Completion: Multivariate Signal Recovery in Computer Vision

Performing Group Difference Testing on Graph Structured Data From GANs: Analysis and Applications in Neuroimaging

Generative adversarial networks (GANs) have emerged as a powerful generative model in computer vision. Given their impressive abilities in generating highly realistic images, they are also being used in novel ways in applications in the life sciences. This raises an interesting question when GANs are used in scientific or biomedical studies. Consider the setting where we are restricted to only using the samples from a trained GAN for downstream group difference analysis (and do not have direct access to the real data). Will we obtain similar conclusions? In this work, we explore if "generated" data, i.e., sampled from such GANs can be used for performing statistical group difference tests in cases versus controls studies, common across many scientific disciplines. We provide a detailed analysis describing regimes where this may be feasible. We complement the technical results with an empirical study focused on the analysis of cortical thickness on brain mesh surfaces in an Alzheimer's disease dataset. To exploit the geometric nature of the data, we use simple ideas from spectral graph theory to show how adjustments to existing GANs can yield improvements. We also give a generalization error bound by extending recent results on Neural Network Distance. To our knowledge, our work offers the first analysis assessing whether the Null distribution in "healthy versus diseased subjects" type statistical testing using data generated from the GANs coincides with the one obtained from the same analysis with real data. The code is available at https://github.com/yyxiongzju/GLapGAN.

Ten questions concerning occupant health in buildings during normal operations and extreme events including the COVID-19 pandemic

Even before the COVID-19 pandemic, people spent on average around 90% of their time indoors. Now more than ever, with work-from-home orders in place, it is crucial that we radically rethink the design and operation of buildings. Indoor Environmental Quality (IEQ) directly affects the comfort and well-being of occupants. When IEQ is compromised, occupants are at increased risk for many diseases that are exacerbated by both social and economic forces. In the U.S. alone, the annual cost attributed to sick building syndrome in commercial workplaces is estimated to be between $10 billion to $70 billion. It is imperative to understand how parameters that drive IEQ can be designed properly and how buildings can be operated to provide ideal IEQ to safeguard health. While IEQ is a fertile area of scholarship, there is a pressing need for a systematic understanding of how IEQ factors impact occupant health. During extreme events, such as a global pandemic, designers, facility managers, and occupants need pragmatic guidance on reducing health risks in buildings. This paper answers ten questions that explore the effects of buildings on the health of occupants. The study establishes a foundation for future work and provides insights for new research directions and discoveries.