Recently, alternating direction method of multipliers (ADMM) attracts much attentions from
various fields and there are many variant versions tailored for different models. Moreover, its …

Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many
applications ranging from robustness certification of classifiers to stability analysis of closed …

This monograph covers some recent advances in a range of acceleration techniques
frequently used in convex optimization. We first use quadratic optimization problems to …

Abstract Plug-and-play (PnP) is a non-convex framework that integrates modern denoising
priors, such as BM3D or deep learning-based denoisers, into ADMM or other proximal …

Motivated by federated learning, we consider the hub-and-spoke model of distributed
optimization in which a central authority coordinates the computation of a solution among …

Spikes and rhythms organize control and communication in the animal world, in contrast to
the bits and clocks of digital technology. As continuous-time signals that can be counted …

Plug-and-play priors (PnP) is a powerful framework for regularizing imaging inverse
problems by using advanced denoisers within an iterative algorithm. Recent experimental …

Implicit-depth models such as Deep Equilibrium Networks have recently been shown to
match or exceed the performance of traditional deep networks while being much more …

Regularized inversion methods for image reconstruction are used widely due to their
tractability and their ability to combine complex physical sensor models with useful regularity …

Policy gradient methods are among the most effective methods for large-scale reinforcement
learning, and their empirical success has prompted several works that develop the …