GPU-accelerated adjoint algorithmic differentiation

Abstract Many scientific problems such as classifier training or medical image reconstruction can be expressed as minimization of differentiable real-valued cost functions and solved with iterative gradient-based methods. Adjoint algorithmic differentiation (AAD) enables automated computation of gradients of such cost functions implemented as computer programs. To backpropagate adjoint derivatives, excessive memory is potentially required to store the intermediate partial derivatives on a dedicated da... Title of program: AD-GPU Catalogue Id: AEYX_v1_0 Nature of problem Gradients are required for many optimization problems, e.g. classifier training or nonlinear image reconstruction. Often, the function, of which the gradient is required, can be implemented as a computer program. Then, algorithmic differentiation methods can be used to compute the gradient. Depending on the approach this may result in excessive requirements of computational resources, i.e. memory and arithmetic computations. GPUs provide massive computational resources but require special consid ... Versions of this program held in the CPC repository in Mendeley Data AEYX_v1_0; AD-GPU; 10.1016/j.cpc.2015.10.027 This program has been imported from the CPC Program Library held at Queen's University Belfast (1969-2018)摘要 诸多科学问题（如分类器训练、医学图像重建）均可表述为可微实值代价函数的最小化问题，并可通过基于梯度的迭代方法求解。伴随算法微分（Adjoint Algorithmic Differentiation, AAD）可自动计算以计算机程序实现的此类代价函数的梯度。为反向传播伴随导数，可能需要大量内存以将中间偏导数存储于专用的da...（原文截断）。 程序名称：AD-GPU 目录编号：AEYX_v1_0 问题本质：诸多优化问题（如分类器训练或非线性图像重建）均需要求解梯度。通常，需求取梯度的函数可通过计算机程序实现，此时可使用算法微分方法计算梯度。根据所采用的方法不同，这可能会导致计算资源（内存与算术运算）的过度消耗。图形处理器（Graphics Processing Unit, GPU）具备海量计算资源，但需要特殊的consid...（原文截断）。 Mendeley数据集中的CPC程序库所收录的该程序版本：AEYX_v1_0；AD-GPU；10.1016/j.cpc.2015.10.027 本程序源自贝尔法斯特女王大学所藏的CPC程序库（1969-2018年）

搜集汇总

背景与挑战

背景概述

该数据集聚焦于GPU加速的伴随算法微分（AAD）技术，旨在解决科学优化问题（如分类器训练和医学图像重建）中梯度计算的自动化需求。它通过利用GPU的大规模计算资源来优化传统AAD方法可能面临的内存和算术计算资源消耗问题，从而提高效率。数据集包括程序版本和来源信息，适用于需要高效梯度计算的科研和工程应用。