Zachary Frangella — accepted AI-conference papers

2025

Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project

Pratik Rathore, Zachary Frangella, Sachin Garg, Shaghayegh Fazliani, Michal Derezinski, Madeleine Udell

NeurIPS 2025poster

Gaussian processes (GPs) play an essential role in biostatistics, scientific machine learning, and Bayesian optimization for their ability to provide probabilistic predictions and model uncertainty. However, GP inference struggles to scale to large datasets (which are common in modern applications),…

Cited by 0 Source ↗code ↗Scholar ↗

2024

CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks

Miria Feng, Zachary Frangella, Mert Pilanci

NeurIPS 2024poster

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 ImageNet, which are ubiquitous in modern deep learning. This significantly improves upon prior work, which has been restrict…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

Challenges in Training PINNs: A Loss Landscape Perspective

Pratik Rathore, Weimu Lei, Zachary Frangella, Lu Lu, Madeleine Udell

ICML 2024oral

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 minimizing the PINN loss function, particularly due to ill-conditioning caused by differential operators in the residual…

Cited by 68 Source ↗PDF ↗code ↗Scholar ↗

2022

NysADMM: faster composite convex optimization via low-rank approximation

Shipu Zhao, Zachary Frangella, Madeleine Udell

ICML 2022spotlight

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 Direction Method of Multipliers (ADMM) by constructing a preconditioner for the ADMM subproblem from a randomized low-rank Ny…

Cited by 16 Source ↗PDF ↗Scholar ↗

2021

Can we globally optimize cross-validation loss? Quasiconvexity in ridge regression

William T. Stephenson, Zachary Frangella, Madeleine Udell, Tamara Broderick

NeurIPS 2021poster

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 widely used for hyperparameter tuning in these models, but do practical methods minimize the true out-of-sample loss? A re…

Cited by 16 Source ↗PDF ↗Scholar ↗