Abstract: Photoplethysmography (PPG) signals are essential for non-invasive cardiovascular monitoring, yet dynamic noise, including motion artifacts, significantly degrades downstream deep learning ...

Abstract: We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the ...

In this repository, we provide a PyTorch implementation of DeepLabV3 neural segmentation networks with Lipschitz constant estimates. Furthermore, we leverage these constants to efficiently certify the ...

We consider the problem of estimating a vector from its noisy measurements using a prior specified only through a denoising function. Recent work on plug- and-play priors (PnP) and ...

I am currently taking new patients. I am a clinical psychologist and Assistant Professor at Brigham and Women's Hospital / Harvard Medical School. In my private practice, I work with clients on ...

The monograph provides a detailed and comprehensive presentation of the rich and beautiful theory of unilateral variational analysis in infinite dimensions. It is divided into two volumes named Part I ...