| Challenges in Training PINNs: A Loss Landscape Perspective P Rathore, W Lei, Z Frangella, L Lu, M Udell International Conference on Machine Learning, 42159-42191, 2024 | 186 | 2024 |
| SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates Z Frangella, P Rathore, S Zhao, M Udell SIAM Journal on Mathematics of Data Science 6 (4), 1173-1204, 2024 | 14* | 2024 |
| Promise: Preconditioned stochastic optimization methods by incorporating scalable curvature estimates Z Frangella, P Rathore, S Zhao, M Udell Journal of Machine Learning Research 25 (346), 1-57, 2024 | 11 | 2024 |
| Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression P Rathore, Z Frangella, J Yang, M Dereziński, M Udell arXiv preprint arXiv:2407.10070, 2025 | 7* | 2025 |
| Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project P Rathore, Z Frangella, S Garg, S Fazliani, M Dereziński, M Udell arXiv preprint arXiv:2505.13723, 2025 | 2 | 2025 |
| There are no Cube-free Descartes Numbers with Exactly Seven Distinct Prime Factors P Rathore arXiv preprint arXiv:1808.10027, 2018 | | 2018 |
Zachary FrangellaResearch Scientist, Granica.aiVerified email at stanford.edu
