My current research interest is in statistical aspects of machine learning. Some concrete problems include imbalanced classification, adversarial examples, and other variations on statistical learning. I also work on applied problems in statistical climate prediction and theoretical questions in networks.

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. As an example, I studied whether a network explains the propagation of a particular process and how to construct networks that explain processes from data.

## Papers

Leqi, L., Khim, J., Prasad, A., and Ravikumar, P. 2020. Uniform Convergence of Rank-Weighted Learning. Proceedings of the 37th International Conference on Machine Learning.

Xu, Z., Dan, C., Khim, J., and Ravikumar, P. 2020. Class-Weighted Classification: Trade-offs and Robust Approaches. Proceedings of the 37th International Conference on Machine Learning. Arxiv.

Khim, J., Xu, Z., and Singh, S. 2020. Multiclass Classification via Class-Weighted Nearest Neighbors. Arxiv.

Khim, J. and Loh, P. 2020. Permutation Tests for Infection Graphs. Journal of the American Statistical Association, DOI: 10.1080/01621459.2019.1700128. Arxiv. Journal.

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

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

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