4 papers
Goal-oriented learning of stochastic differential equations using error bounds on path-space observables
Joanna Zou, Han Cheng Lie, Youssef Marzouk
Stochastic differential equations (SDEs), which serve as the governing equations for dynamical systems in a broad range of applications, can become cost-prohibitive for numerical s…
Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
Joanna Zou, Fraser Birks, Dallas Foster +1
Machine learning interatomic potentials (MLIPs) enable efficient and accurate atomistic simulations but depend critically on the quality and diversity of the training data. We intr…
Precise asymptotic analysis of Sobolev training for random feature models
Katharine E Fisher, Matthew TC Li, Youssef Marzouk +1
Gradient information is widely useful and available in applications, and is therefore natural to include in the training of neural networks. Yet little is known theoretically about…
Can Bayesian Neural Networks Make Confident Predictions?
Katharine Fisher, Youssef Marzouk
Bayesian inference promises a framework for principled uncertainty quantification of neural network predictions. Barriers to adoption include the difficulty of fully characterizing…