Research
1) Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
Kedar Karhadkar, Michael Murray, and Guido Montúfar. Accepted to NeurIPS 2024. Preprint: arXiv:2405.14630.
2) Benign overfitting in leaky ReLU networks with moderate input dimension
Kedar Karhadkar, Erin George, Michael Murray, Guido Montúfar, and Deanna Needell. Accepted to NeurIPS 2024. Preprint: arXiv:2403.06903.
3) Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape
Kedar Karhadkar, Michael Murray, Hanna Tseran, and Guido Montúfar. Transactions on Machine Learning Research. Preprint: arXiv:2305.19510.
4) FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
Kedar Karhadkar, Pradeep Kr. Banerjee, and Guido Montúfar. The Eleventh International Conference on Learning Representations (ICLR 2023). Preprint: arXiv:2210.11790
5) Sum index and difference index of simple graphs
Joshua Harrington, Eugene Henninger-Voss, Kedar Karhadkar, Emily Robinson, and Tony W.H. Wong. Discrete Applied Mathematics (2023). Preprint: arxiv:2008.09265.
6) Oversquashing in GNNs through the lens of information contraction and graph expansion
Pradeep Kr. Banerjee, Kedar Karhadkar, Yu Guang Wang, Uri Alon, and Guido Montúfar. 58th Annual Allerton Conference on Communication, Control and Computing (2022). Preprint: arXiv:2208.03471.
7) Two dependent probabilistic chip-collecting games
Joshua Harrington, Kedar Karhadkar, Madeline Kohutka, Tessa Stevens, and Tony W.H. Wong. Discrete Applied Mathematics (2021).
8) Parity of the partition function \(p(n, k)\)
Kedar Karhadkar. International Journal of Number Theory (2019). Preprint: arXiv:1809.07459.
9) Lattice models, differential forms, and the Yang-Baxter equation
Kedar Karhadkar. Preprint: arXiv:2207.13282