Max Daniels

I’m interested in the intrinsic structures hidden inside data and the conditions under which these structures can be recovered, compressed, or visualized. I am lucky to have been advised by Dr. Paul Hand and Dr. Misha Kilmer on topics in imaging inverse problems, generative modeling with deep neural networks, and compression methods for multiway data.

Contact Me

Please reach out by email at [lastname][email protected] or on social media (Twitter, LinkedIn, and GitHub).

Selected Work

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

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

In an imaging inverse problem, one must recover missing information about a target image using prior assumptions on the image structure. We show that Invertible Neural Networks can be used to vastly outperform classical approaches when one has access to a dataset of known images.

Statistical Distances and Their Implications to GAN Training.

Max Daniels. Presented at VISxAI workshop at IEEE VIS 2019. Honorable mention for best submission.

This is an interactive article about the role of statistical distances like Kullback Leibler Divergence and Earth Mover's Distance in training Generative Adversarial Networks (GANs).

An Overview of Graph Spectral Clustering and Partial Differential Equations.

Max Daniels*, Catherine Huang*, Chloe Makdad*, Shubham Makharia*. Product of a 2020 summer undergraduate research program run by the Institute for Computational and Experimental Research in Mathematics.

Clustering is a useful tool in data analysis. We explain the connection between the graph spectral clustering algorithm and the physical process of heat diffusion.


Barry Goldwater Award. Recipient of a Barry Goldwater award for outstanding undergraduate research (national award, one of 22 recipients in computer science, received as a sophomore).

Summit Research Award. Recipient of a Northeastern University internal research award of $3000.

University Honors Early Research Award. Recipient of a Northeastern University Honors Program award for outstanding research by a freshman or sophomore student in the amount of $1000.


Semantic Manipulations through Learned Information Representations. March 2020.

Invited talk given at Brown University's Symposium for Undergraduates in the Mathematical Sciences.

The talk and slides begin with an overview of Noise Contrastive Estimation for generative modeling. They explain the Word2Vec algorithm as a simplification of NCE with interpretable parameters, then explain how Generative Adversarial training uses ideas from NCE to learn to efficiently approximately sample a data distribution.

ASME Machine Learning Workshop. June 2019.

Co-organized three week workshop on machine learning for Northeastern's chapter of the American Society of Mechanical Engineers.

Emphasis in the workshop was placed on regression, decision trees, and boosting models.


I care about educational outreach and activism. Here are some of the ways I'm involved: