40 citations · 46 across the 14 of their papers we have counts for
15 papers
GPU-Enabled Large-Scale Optimization Using Randomized Linear Algebra
Pratik Rathore, Zachary Frangella, Parth Nobel +2
This paper introduces rlaopt, a PyTorch-based package for large-scale optimization and scientific computing using randomized numerical linear algebra (RandNLA). Despite substantial…
Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
Pratik Rathore, Zachary Frangella, Sachin Garg +3
Gaussian processes (GPs) play an essential role in biostatistics, scientific machine learning, and Bayesian optimization for their ability to provide probabilistic predictions and…
Enhancing Physics-Informed Neural Networks Through Feature Engineering
Shaghayegh Fazliani, Zachary Frangella, Madeleine Udell
Physics-Informed Neural Networks (PINNs) seek to solve partial differential equations (PDEs) with deep learning. Mainstream approaches that deploy fully-connected multi-layer deep…
SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning
Jingruo Sun, Zachary Frangella, Madeleine Udell
Regularized empirical risk minimization (rERM) has become important in data-intensive fields such as genomics and advertising, with stochastic gradient methods typically used to so…
CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
Miria Feng, Zachary Frangella, Mert Pilanci
We introduce the CRONOS algorithm for convex optimization of two-layer neural networks. CRONOS is the first algorithm capable of scaling to high-dimensional datasets such as ImageN…
Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression
Pratik Rathore, Zachary Frangella, Jiaming Yang +2
Kernel ridge regression (KRR) is a fundamental computational tool, appearing in problems that range from computational chemistry to health analytics, with a particular interest due…
Challenges in Training PINNs: A Loss Landscape Perspective
Pratik Rathore, Weimu Lei, Zachary Frangella +2
This paper explores challenges in training Physics-Informed Neural Networks (PINNs), emphasizing the role of the loss landscape in the training process. We examine difficulties in…
GeNIOS: an (almost) second-order operator-splitting solver for large-scale convex optimization
Theo Diamandis, Zachary Frangella, Shipu Zhao +2
We introduce the GEneralized Newton Inexact Operator Splitting solver (GeNIOS) for large-scale convex optimization. GeNIOS speeds up ADMM by approximately solving approximate subpr…
PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates
Zachary Frangella, Pratik Rathore, Shipu Zhao +1
This paper introduces PROMISE (econditioned Stochastic ptimization ethods by ncorporating calable Curvature $\textbf{E}…
Robust, randomized preconditioning for kernel ridge regression
Mateo Díaz, Ethan N. Epperly, Zachary Frangella +2
We investigate preconditioned conjugate gradient methods for kernel ridge regression (KRR) problems with a moderate to large number of data points (). We dev…
On the (linear) convergence of Generalized Newton Inexact ADMM
Zachary Frangella, Theo Diamandis, Bartolomeo Stellato +1
This paper presents GeNI-ADMM, a framework for large-scale composite convex optimization that facilitates theoretical analysis of both existing and new approximate ADMM schemes. Ge…
SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
Zachary Frangella, Pratik Rathore, Shipu Zhao +1
SketchySGD improves upon existing stochastic gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian and by introducing an automa…
NysADMM: faster composite convex optimization via low-rank approximation
Shipu Zhao, Zachary Frangella, Madeleine Udell
This paper develops a scalable new algorithm, called NysADMM, to minimize a smooth convex loss function with a convex regularizer. NysADMM accelerates the inexact Alternating Direc…
Randomized Nyström Preconditioning
Zachary Frangella, Joel A. Tropp, Madeleine Udell
This paper introduces the Nyström PCG algorithm for solving a symmetric positive-definite linear system. The algorithm applies the randomized Nyström method to form a low-rank appr…
Can we globally optimize cross-validation loss? Quasiconvexity in ridge regression
William T. Stephenson, Zachary Frangella, Madeleine Udell +1
Models like LASSO and ridge regression are extensively used in practice due to their interpretability, ease of use, and strong theoretical guarantees. Cross-validation (CV) is wide…