With the growing interest in the field of artificial materials, more advanced and sophisticated
wave functionalities are required from phononic crystals and acoustic metamaterials. Due to …

Simulation is increasingly being used for generating large labelled datasets in many
machine learning problems. Recent methods have focused on adjusting simulator …

In modern supervised learning, many deep neural networks are able to interpolate the data:
the empirical loss can be driven to near zero on all samples simultaneously. In this work, we …

We describe and demonstrate an optimization-based X-ray image reconstruction framework
called Adorym. Our framework provides a generic forward model, allowing one code …

Influence diagnostics such as influence functions and approximate maximum influence
perturbations are popular in machine learning and in AI domain applications. Influence …

The deep unfolding network represents a promising research avenue in image restoration.
However, most current deep unfolding methodologies are anchored in first-order …

We propose a continuous-time second-order optimization algorithm for solving
unconstrained convex optimization problems with bounded Hessian. We show that this …

Inspired by Gauss-Newton-like methods, we study the benefit of leveraging the structure of
deep learning objectives, namely, the composition of a convex loss function and of a …

We propose a novel method for training deep neural networks that are capable of
interpolation, that is, driving the empirical loss to zero. At each iteration, our method …

Semismooth Newton is a powerful tool to tackle the regularization problems in image
restoration. Compared to other optimization methods such as alternating direction method of …