Publications

Here is a list of my publications (organized by venue) and preprints.

* denotes equal contribution

Thesis

• Randomized Numerical Linear Algebra for Large-Scale Optimization
  Zachary Frangella
  Stanford University Thesis, 2025

Journal Publications

• On the Linear Convergence of Generalized Newton Inexact ADMM
  Zachary Frangella, Theo Diamandis, Bartolomeo Stellato, Madeleine Udell
  Accepted, Transactions on Machine Learning Research, 2025
  [code]

• GeNIOS: an (almost) second-order operator-splitting solver for large-scale convex optimization
  Theo Diamandis, Zachary Frangella, Shipu Zhao, Bartolomeo Stellato, Madeleine Udell
  Accepted, Mathematical Programming Computation, 2025
  [code]

• Enhancing Physics-Informed Neural Networks Through Feature Engineering
  Shaghayegh Fazliani, Zachary Frangella, Madeleine Udell
  Transactions on Machine Learning Research, 2025

• PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates
  Zachary Frangella*, Pratik Rathore*, Shipu Zhao, Madeleine Udell
  Journal of Machine Learning Research, 2024
  [code]

• SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
  Zachary Frangella, Pratik Rathore, Shipu Zhao, Madeleine Udell
  SIAM Journal on Mathematics of Data Science, 2024
  [code]

• Randomized Nyström Preconditioning
  Zachary Frangella, Joel A. Tropp, Madeleine Udell
  SIAM Journal on Matrix Analysis and Applications, 2023

Conference Publications

• Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
  Pratik Rathore, Zachary Frangella, Sachin Garg, Shaghayegh Fazliani, Michał Dereziński, Madeleine Udell
  Accepted, Advances in Neural Information Processing Systems, 2025

• CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
  Miria Feng, Zachary Frangella, Mert Pilanci
  Advances in Neural Information Processing Systems, 2024
  [code]

• Challenges in Training PINNs: A Loss Landscape Perspective
  Pratik Rathore, Weimu Lei, Zachary Frangella, Lu Lu, Madeleine Udell
  International Conference on Machine Learning, 2024, Oral (top 1.5% of submissions)
  [code]

• NysADMM: faster composite convex optimization via low-rank approximation
  Shipu Zhao*, Zachary Frangella*, Madeleine Udell
  International Conference on Machine Learning, 2022

• Can we globally optimize cross-validation loss? Quasiconvexity in ridge regression
  William T. Stephenson, Zachary Frangella, Madeleine Udell, Tamara Broderick
  Advances in Neural Information Processing Systems, 2021

In the Pipeline

• Robust, randomized preconditioning for kernel ridge regression
  Mateo Diaz, Ethan N. Epperly, Zachary Frangella, Joel A. Tropp, Robert J. Webber
  Submitted
  [code]

• Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression
  Pratik Rathore, Zachary Frangella, Jiaming Yang, Michał Dereziński, Madeleine Udell
  Submitted
  [code]

• SAPPHIRE: Preconditioned Stochcastic Variance Reduction for Faster Large-Scale Statistical Learning
  Jingruo Sun, Zachary Frangella, Madeleine Udell
  Submitted
  [code]