Mara Daniels

maradan_
Scholar : Twitter : GitHub.

I am an Applied Mathematics PhD candidate at MIT. My advisor is Phillipe Rigollet. I am interested in developing theory and principled methodologies for deep machine learning, often in the context of image generation and imaging or spatial inverse problems. Previously, I was fortunate to work under the supervision of Dr. Paul Hand at Northeastern University and Dr. Lenka Zdeborová at EPFL.

Image

News

I am actively searching for motivated collaborators to work on Splat Regression Modeling. If you are interested, please email me with a description of your background and interests.

Publications

* indicates equal contribution.

Splat Regression Models

Mara Daniels, Philippe Rigollet.

On the Contractivity of Stochastic Interpolation Flow

Mara Daniels.

Uncertainty-Aware Diagnostics for Physics-Informed Machine Learning

Mara Daniels, Liam Hodgkinson, Michael Mahoney.

Multi-layer State Evolution Under Random Convolutional Design.

Mara Daniels, Cédric Gerbelot, Florent Krzakala, Lenka Zdeborová. Published in NeurIPS 2022.

Score-based Generative Neural Networks for Large-Scale Optimal Transport.

Mara Daniels Tyler Maunu, Paul Hand. Published in NeurIPS 2021.

Generator Surgery for Compressed Sensing

Jung Yeon Park, Niklas Smedemark-Marguilies, Mara Daniels, Rose Yu, Jan-Willem van de Meent, Paul Hand. Presented at NeurIPS 2020 Deep Inverse Workshop.

Invertible generative models for inverse problems: mitigating representation error and dataset bias.

Muhammad Asim, Mara Daniels, Oscar Leong, Paul Hand, and Ali Ahmed. Published in ICML 2020.

Miscellany...