5 papers · 1 filter
Can neural operators always be continuously discretized?
Takashi Furuya, Michael Puthawala, Maarten V. de Hoop +1
We consider the problem of discretization of neural operators between Hilbert spaces in a general framework including skip connections. We focus on bijective neural operators throu…
Learning sparsity-promoting regularizers for linear inverse problems
Giovanni S. Alberti, Ernesto De Vito, Tapio Helin +3
This paper introduces a novel approach to learning sparsity-promoting regularizers for solving linear inverse problems. We develop a bilevel optimization framework to select an opt…
Inverse problems for quantum graph associated with square and hexagonal lattices
K. Ando, E. Blåsten, P. Exner +5
We solve inverse problems from the D-N map for the quantum graph on a finite domain in a square lattice and that on a hexagonal lattice, as well as inverse scattering problems from…
An Unconditional Representation of the Conditional Score in Infinite-Dimensional Linear Inverse Problems
Fabian Schneider, Duc-Lam Duong, Matti Lassas +2
Score-based diffusion models (SDMs) have emerged as a powerful tool for sampling from the posterior distribution in Bayesian inverse problems. However, existing methods often requi…
Mixtures of Neural Operators Reduce Active Complexity in Operator Learning
Anastasis Kratsios, Takashi Furuya, Jose Antonio Lara Benitez +2
Operator-learning systems are not governed solely by total parameter count; for one query, the relevant bottleneck can be the model that must be loaded and evaluated. We study this…