collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models

Conor Rowan

Scientists have historically relied on mathematical models based on differential equations to relate system inputs -- forces, fluxes, or heat sources -- to outputs, such as displac…

cs.LG2026

On the definition and importance of interpretability in scientific machine learning

Conor Rowan, Alireza Doostan

Though neural networks trained on large datasets have been successfully used to describe and predict many physical phenomena, there is a sense among scientists that, unlike traditi…

cs.LG2026

Visualizing the loss landscapes of physics-informed neural networks

Conor Rowan, Finn Murphy-Blanchard

Training a neural network requires navigating a high-dimensional, non-convex loss surface to find parameters that minimize this loss. In many ways, it is surprising that optimizers…

cs.LG2025

On the failure of ReLU activation for physics-informed machine learning

Conor Rowan

Physics-informed machine learning uses governing ordinary and/or partial differential equations to train neural networks to represent the solution field. Like any machine learning…

cs.LG2025

Finding geodesics with the Deep Ritz method

Conor Rowan

Geodesic problems involve computing trajectories between prescribed initial and final states to minimize a user-defined measure of distance, cost, or energy. They arise throughout…

cs.LG2025

Nonlinear discretizations and Newton's method: characterizing stationary points of regression objectives

Conor Rowan

Second-order methods are emerging as promising alternatives to standard first-order optimizers such as gradient descent and ADAM for training neural networks. Though the advantages…