走得更快,看得更远:使用JAX进行易损库存控制的图形处理单元加速值代和模拟.
Joseph Farrington1, Wai Keong Wong1,2,3,4, Kezhi Li1
1Institute of Health Informatics, University College London, London, UK.
Annals of operations research
|August 18, 2025
概括
我们使用图形处理单元 (GPU) 开发了一种更快的价值代方法,用于易损坏的库存管理. 这种方法使复杂的库存问题在计算上可行,实现接近最佳的补充政策.
科学领域:
- 运营研究 运营研究
- 计算科学 计算科学
- 库存管理 库存管理
背景情况:
- 值代对于易损坏的库存问题是有效的,但由于大状态空间而计算密集.
- 图形处理单元 (GPU) 提供并行处理能力,可以加速值代.
- 在运营研究中采用GPU落后于机器学习,原因是可访问性挑战.
研究的目的:
- 实施和评估一个GPU加速的价值代方法,用于易损坏的库存问题.
- 为了证明以前难以解决的问题大小和复杂性的值代的可行性.
- 将GPU加速值代策略与启发式策略的性能进行比较.
主要方法:
- 使用JAX库实现GPU加速的实现值代和马尔科夫决策过程模拟器.
- 利用JAX的函数转换和编译器来实现高效的GPU硬件利用.
- 通过JAX中的模拟优化开发了启发式策略,使候选参数的并行评估成为可能.
主要成果:
- 成功地将该方法应用于超过1600万个状态和复杂特征 (如产品替代) 的问题.
- 实现了接近最佳的补充政策,启发式政策显示最大最佳性差距为2.49%.
- 展示了显著的计算加速,使大规模的价值代变得实用.
结论:
- 使用JAX的GPU加速值代显著提高易损坏库存管理的计算效率.
- 这种方法将价值代的适用性扩展到复杂的,大规模的运营研究问题.
- 一般方法可适应各种运营研究挑战,需要在GPU上进行大规模并行计算.
相关概念视频
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
100
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
100
01:13Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
126
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
126
01:15Introduction to Statistical Process Control
250
Statistical Process Control (SPC) is a method used to monitor and control quality within processes, particularly in manufacturing and service delivery, by employing statistical methods. SPC aims to distinguish between natural (common cause) variation and variation due to specific changes or events (special cause), allowing for timely improvements and sustained quality. The control chart, a pivotal tool in SPC, visually displays data over time alongside a central line of upper and lower control...
250
01:20Parallel Processing
225
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
225
01:21Distributed Loads: Problem Solving
731
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
731
01:17Accelerating Fluids
1.4K
When a fluid is in constant acceleration, the pressure and buoyant force equations are modified. Suppose a beaker is placed in an elevator accelerating upward with a constant acceleration, a. In the beaker, assume there is a thin cylinder of height h with an infinitesimal cross-sectional area, ΔS.
The motion of the liquid within this infinitesimal cylinder is considered to obtain the pressure difference. Three vertical forces act on this liquid:
The motion of the liquid within this infinitesimal cylinder is considered to obtain the pressure difference. Three vertical forces act on this liquid:
1.4K