# Large-Scale Inventory Optimization: A Recurrent-Neural-Networks-Inspired Simulation Approach

arXiv: https://arxiv.org/abs/2201.05868 · HTML: https://mlsanity.com/paper/2201.05868/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 47 references that are in the map.
- First posted on arXiv 15 Jan 2022.

## Builds on (most cited first, 5 of 5)

- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Automatic differentiation in machine learning: a survey](https://mlsanity.com/paper/1502.05767/) (2015)
- [Image Captioning with Semantic Attention](https://mlsanity.com/paper/1603.03925/) (2016)
- [Theoretical insights into the optimization landscape of over-parameterized shallow neural networks](https://mlsanity.com/paper/1707.04926/) (2017)
- [EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding](https://mlsanity.com/paper/1507.08240/) (2015)

## Built on by (most cited first, 2 of 2)

- [Optimal low-rank stochastic gradient estimation for LLM training](https://mlsanity.com/paper/2603.20632/) (2026)
- [Supervised Learning for the (s,S) Inventory Model with General Interarrival Demands and General Lead Times](https://mlsanity.com/paper/2601.12900/) (2026)

## Abstract (arXiv)

Many large-scale production networks include thousands types of final products and tens to hundreds thousands types of raw materials and intermediate products. These networks face complicated inventory management decisions, which are often too complicated for inventory models and too large for simulation models. In this paper, by combing efficient computational tools of recurrent neural networks (RNN) and the structural information of production networks, we propose a RNN inspired simulation approach that may be thousands times faster than existing simulation approach and is capable of solving large-scale inventory optimization problems in a reasonable amount of time.