activity
20092026
most citedDeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators

3.4k citations · 27.2k across the 213 of their papers we have counts for

collaborators
Showing 2017 · stat.MLShow all

2 papers · 2 filters

stat.ML2017

Parametric Gaussian Process Regression for Big Data

Maziar Raissi

This work introduces the concept of parametric Gaussian processes (PGPs), which is built upon the seemingly self-contradictory idea of making Gaussian processes parametric. Paramet…

stat.ML2017★ 16 cited

Numerical Gaussian Processes for Time-dependent and Non-linear Partial Differential Equations

Maziar Raissi, Paris Perdikaris, George Em Karniadakis

We introduce the concept of numerical Gaussian processes, which we define as Gaussian processes with covariance functions resulting from temporal discretization of time-dependent p…