# Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case

arXiv: https://arxiv.org/abs/2103.10142 · HTML: https://mlsanity.com/paper/2103.10142/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis](https://mlsanity.com/paper/1701.05927/) (2017)
- [Efficient Execution of Quantized Deep Learning Models: A Compiler Approach](https://mlsanity.com/paper/2006.10226/) (2020)

## Built on by (most cited first, 6 of 6)

- [CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows](https://mlsanity.com/paper/2106.05285/) (2021)
- [New directions for surrogate models and differentiable programming for High Energy Physics detector simulation](https://mlsanity.com/paper/2203.08806/) (2022)
- [Latent Space Refinement for Deep Generative Models](https://mlsanity.com/paper/2106.00792/) (2021)
- [Image and Point-cloud Classification for Jet Analysis in High-Energy Physics: A survey](https://mlsanity.com/paper/2403.11934/) (2024)
- [BitHEP -- The Limits of Low-Precision ML in HEP](https://mlsanity.com/paper/2504.03387/) (2025)
- [From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks](https://mlsanity.com/paper/2509.25933/) (2025)

## Abstract (arXiv)

Deep learning is finding its way into high energy physics by replacing traditional Monte Carlo simulations. However, deep learning still requires an excessive amount of computational resources. A promising approach to make deep learning more efficient is to quantize the parameters of the neural networks to reduced precision. Reduced precision computing is extensively used in modern deep learning and results to lower execution inference time, smaller memory footprint and less memory bandwidth. In this paper we analyse the effects of low precision inference on a complex deep generative adversarial network model. The use case which we are addressing is calorimeter detector simulations of subatomic particle interactions in accelerator based high energy physics. We employ the novel Intel low precision optimization tool (iLoT) for quantization and compare the results to the quantized model from TensorFlow Lite. In the performance benchmark we gain a speed-up of 1.73x on Intel hardware for the quantized iLoT model compared to the initial, not quantized, model. With different physics-inspired self-developed metrics, we validate that the quantized iLoT model shows a lower loss of physical accuracy in comparison to the TensorFlow Lite model.