中文
相关论文

相关论文: An Optimal Control Approach for Inverse Problems w…

200 篇论文

Optimal control provides a principled framework for transforming dynamical system models into intelligent decision-making, yet classical computational approaches are often too expensive for real-time deployment in dynamic or uncertain…

最优化与控制 · 数学 2026-01-01 Wuzhe Xu , Jiequn Han , Rongjie Lai

In this paper we explore the relation between distributionally robust learning and different forms of regularization to enforce robustness of deep neural networks. In particular, starting from a concrete min-max distributionally robust…

最优化与控制 · 数学 2022-03-29 Camilo Garcia Trillos , Nicolas Garcia Trillos

In this chapter, we are concerned with inverse optimal control problems, i.e., optimization models which are used to identify parameters in optimal control problems from given measurements. Here, we focus on linear-quadratic optimal control…

最优化与控制 · 数学 2023-11-27 Stephan Dempe , Markus Friedemann , Felix Harder , Patrick Mehlitz , Gerd Wachsmuth

A promising approach to optimal control of nonlinear systems involves iteratively linearizing the system and solving an optimization problem at each time instant to determine the optimal control input. Since this approach relies on online…

最优化与控制 · 数学 2025-01-30 Anran Li , John P. Swensen , Mehdi Hosseinzadeh

We investigate a well-known phenomenon of variational approaches in image processing, where typically the best image quality is achieved when the gradient flow process is stopped before converging to a stationary point. This paradox…

最优化与控制 · 数学 2019-07-23 Alexander Effland , Erich Kobler , Karl Kunisch , Thomas Pock

Sampling-based model predictive control (MPC) has found significant success in optimal control problems with non-smooth system dynamics and cost function. Many machine learning-based works proposed to improve MPC by a) learning or…

机器学习 · 计算机科学 2024-01-08 Sungwook Yang , Chaoying Pei , Ran Dai , Chuangchuang Sun

Unsupervised deep learning approaches have recently become one of the crucial research areas in imaging owing to their ability to learn expressive and powerful reconstruction operators even when paired high-quality training data is scarcely…

计算机视觉与模式识别 · 计算机科学 2023-11-30 Marcello Carioni , Subhadip Mukherjee , Hong Ye Tan , Junqi Tang

The fragility of deep neural networks to adversarially-chosen inputs has motivated the need to revisit deep learning algorithms. Including adversarial examples during training is a popular defense mechanism against adversarial attacks. This…

最优化与控制 · 数学 2020-05-05 Jacob H. Seidman , Mahyar Fazlyab , Victor M. Preciado , George J. Pappas

Inverse problems arise in many applications, especially tomographic imaging. We develop a Learned Alternating Minimization Algorithm (LAMA) to solve such problems via two-block optimization by synergizing data-driven and classical…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Chi Ding , Qingchao Zhang , Ge Wang , Xiaojing Ye , Yunmei Chen

Overparameterized autoencoder models often memorize their training data. For image data, memorization is often examined by using the trained autoencoder to recover missing regions in its training images (that were used only in their…

机器学习 · 计算机科学 2024-06-14 Koren Abitbul , Yehuda Dar

We introduce a method for fast estimation of data-adapted, spatio-temporally dependent regularization parameter-maps for variational image reconstruction, focusing on total variation (TV)-minimization. Our approach is inspired by recent…

Learning-to-optimize is an emerging framework that seeks to speed up the solution of certain optimization problems by leveraging training data. Learned optimization solvers have been shown to outperform classical optimization algorithms in…

最优化与控制 · 数学 2023-02-27 Hong Ye Tan , Subhadip Mukherjee , Junqi Tang , Carola-Bibiane Schönlieb

Attempts from different disciplines to provide a fundamental understanding of deep learning have advanced rapidly in recent years, yet a unified framework remains relatively limited. In this article, we provide one possible way to align…

机器学习 · 计算机科学 2019-10-01 Guan-Horng Liu , Evangelos A. Theodorou

Traditional maximum entropy and sparsity-based algorithms for analytic continuation often suffer from the ill-posed kernel matrix or demand tremendous computation time for parameter tuning. Here we propose a neural network method by convex…

机器学习 · 计算机科学 2022-02-07 Dongchen Huang , Yi-feng Yang

The inherent ill-posed nature of image reconstruction problems, due to limitations in the physical acquisition process, is typically addressed by introducing a regularisation term that incorporates prior knowledge about the underlying…

图像与视频处理 · 电气工程与系统科学 2025-03-11 Naïl Khelifa , Ferdia Sherry , Carola-Bibiane Schönlieb

In this work we present a novel optimization strategy for image reconstruction tasks under analysis-based image regularization, which promotes sparse and/or low-rank solutions in some learned transform domain. We parameterize such…

计算机视觉与模式识别 · 计算机科学 2023-08-11 Iaroslav Koshelev , Stamatios Lefkimmiatis

In this chapter we provide a theoretically founded investigation of state-of-the-art learning approaches for inverse problems from the point of view of spectral reconstruction operators. We give an extended definition of regularization…

数值分析 · 数学 2024-06-05 Martin Burger , Samira Kabri

In this paper, we propose a machine learning (ML) method to learn how to solve a generic constrained continuous optimization problem. To the best of our knowledge, the generic methods that learn to optimize, focus on unconstrained…

机器学习 · 计算机科学 2021-01-05 Seyedrazieh Bayati , Faramarz Jabbarvaziri

Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the-art algorithms focus on approximate sequential optimization…

机器学习 · 计算机科学 2020-04-23 Joe Watson , Hany Abdulsamad , Jan Peters

This paper highlights a parallel between the forward backward sweeping method for optimal control and deep learning training procedures. We reformulate a classical optimal control problem, constrained by a differential equation system, into…

最优化与控制 · 数学 2025-04-23 Wenjing Zhang , Wandi Ding , Huaiping Zhu