My current research interest is in statistical aspects of deep learning. Some topics include statistical learning, nonparametric regression, and adversarial examples. I’m also interested in applications to image and text data.

My PhD research was in network science, meaning problems inspired by social, biological, computer, and other types of networks. Network science draws on contributions from researchers in many fields, such as economics, computer science, physics, applied math, engineering, probability, and statistics. Specifically, I studied whether a network explains the propagation of a particular process and how to construct networks that explain processes from data.


Khim, J., Jog, V., and Loh, P. 2019. Adversarial Influence Maximization. IEEE International Symposium on Information Theory. Arxiv.

Khim, J. and Loh, P. 2018. Adversarial Risk Bounds for Binary Classification via Function Transformation. Submitted. Arxiv.

Khim, J. and Loh, P. 2018. A theory of maximum likelihood for weighted infection graphs. Submitted. Arxiv.

Khim, J. and Loh, P. 2017. Permutation Tests for Infection Graphs. Submitted. Arxiv.

Khim, J. and Loh, P. 2017. Confidence sets for the source of a diffusion in regular trees. IEEE Transactions on Network Science and Engineering. Volume 4, Issue 1. Arxiv. Journal.

Khim, J., Jog, V., and Loh, P. 2016. Computing and maximizing in linear threshold and triggering models. Advances in Neural Information Processing Systems. Conference Paper.