Fusion energy offers the potential for the generation of clean, safe, an...
Most inverse problems from physical sciences are formulated as
PDE-const...
Motivated by the computational difficulties incurred by popular deep lea...
This paper develops and analyzes a stochastic derivative-free optimizati...
A large class of inverse problems for PDEs are only well-defined as mapp...
Can Monte Carlo (MC) solvers be directly used in gradient-based methods ...
We derive an adjoint method for the Direct Simulation Monte Carlo (DSMC)...
Small generalization errors of over-parameterized neural networks (NNs) ...
We propose a new stochastic gradient descent algorithm for finding the g...
We propose an efficient numerical method for computing natural gradient
...
The generalization capacity of various machine learning models exhibits
...
In this paper, we propose to use the general L^2-based Sobolev norms (i....
Applications for kinetic equations such as optimal design and inverse
pr...
The state-of-art seismic imaging techniques treat inversion tasks such a...
Recently, the Wasserstein loss function has been proven to be effective ...
Anderson acceleration (AA) is a technique for accelerating the convergen...
Full waveform inversion (FWI) is today a standard process for the invers...
This work characterizes, analytically and numerically, two major effects...