A survey of recent advances in optimization methods for wireless communications

YF Liu, TH Chang, M Hong, Z Wu… - IEEE Journal on …, 2024 - ieeexplore.ieee.org
Mathematical optimization is now widely regarded as an indispensable modeling and
solution tool for the design of wireless communications systems. While optimization has …

A survey on some recent developments of alternating direction method of multipliers

DR Han - Journal of the Operations Research Society of China, 2022 - Springer
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 …

On the theory of policy gradient methods: Optimality, approximation, and distribution shift

A Agarwal, SM Kakade, JD Lee, G Mahajan - Journal of Machine Learning …, 2021 - jmlr.org
Policy gradient methods are among the most effective methods in challenging reinforcement
learning problems with large state and/or action spaces. However, little is known about even …

Optimality and approximation with policy gradient methods in markov decision processes

A Agarwal, SM Kakade, JD Lee… - … on Learning Theory, 2020 - proceedings.mlr.press
Policy gradient (PG) methods are among the most effective methods in challenging
reinforcement learning problems with large state and/or action spaces. However, little is …

Policy gradient method for robust reinforcement learning

Y Wang, S Zou - International conference on machine …, 2022 - proceedings.mlr.press
This paper develops the first policy gradient method with global optimality guarantee and
complexity analysis for robust reinforcement learning under model mismatch. Robust …

Denoising prior driven deep neural network for image restoration

W Dong, P Wang, W Yin, G Shi, F Wu… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Deep neural networks (DNNs) have shown very promising results for various image
restoration (IR) tasks. However, the design of network architectures remains a major …

The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale's 18th problem

MJ Colbrook, V Antun… - Proceedings of the …, 2022 - National Acad Sciences
Deep learning (DL) has had unprecedented success and is now entering scientific
computing with full force. However, current DL methods typically suffer from instability, even …

Global convergence of ADMM in nonconvex nonsmooth optimization

Y Wang, W Yin, J Zeng - Journal of Scientific Computing, 2019 - Springer
In this paper, we analyze the convergence of the alternating direction method of multipliers
(ADMM) for minimizing a nonconvex and possibly nonsmooth objective function, ϕ (x_0 …

Acceleration methods

A d'Aspremont, D Scieur, A Taylor - Foundations and Trends® …, 2021 - nowpublishers.com
This monograph covers some recent advances in a range of acceleration techniques
frequently used in convex optimization. We first use quadratic optimization problems to …

Modern regularization methods for inverse problems

M Benning, M Burger - Acta numerica, 2018 - cambridge.org
Regularization methods are a key tool in the solution of inverse problems. They are used to
introduce prior knowledge and allow a robust approximation of ill-posed (pseudo-) inverses …