My research focuses on reliable machine learning and the design and study of expressive models that are robust to noise and generalize well in out-of-distribution data. Concretely:
- I am interested in understanding the inducative bias of deep networks and properties of existing architectures through empirical and theoretical studies. I am interested in the complete theoretical understanding of (neural/polynomial) networks, including their expressivity, trainability, generalization properties
- The understanding of the inductive bias will enable us to design improved networks. Towards that end, I have worked extensively on polynomial networks (PNs). PNs that capture high-degree interactions between inputs.
- I am interested in the extrapolation properties of existing networks and improving their performance, especially in the context of conditional generative models. In the short-term, I will continue to explore the robustness of these models to malicious attacks, as well as the impact of adversarial perturbations on different classes. In the long-term, I plan to design models that are both robust and fair, and can generalize well to unseen combinations.
I am looking for (under)graduate students who are passionate in working in machine learning. Before you e-mail me, please check out the related section in my site.