# WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic

arXiv: https://arxiv.org/abs/2007.13242 · HTML: https://mlsanity.com/paper/2007.13242/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward](https://mlsanity.com/paper/2402.01799/) (2024)
- [EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs](https://mlsanity.com/paper/2403.02775/) (2024)
- [MKQ-BERT: Quantized BERT with 4-bits Weights and Activations](https://mlsanity.com/paper/2203.13483/) (2022)
- [Accumulator-Aware Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2409.17092/) (2024)
- [Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators](https://mlsanity.com/paper/2401.14110/) (2024)
- [Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision](https://mlsanity.com/paper/2102.13565/) (2021)
- [Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference](https://mlsanity.com/paper/2203.02833/) (2022)
- [DQRM: Deep Quantized Recommendation Models](https://mlsanity.com/paper/2410.20046/) (2024)
- [SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference](https://mlsanity.com/paper/2308.04753/) (2023)
- [BiVM: Accurate Binarized Neural Network for Efficient Video Matting](https://mlsanity.com/paper/2507.04456/) (2025)
- [Efficient DNN-Powered Software with Fair Sparse Models](https://mlsanity.com/paper/2407.02805/) (2024)

## Abstract (arXiv)

Low-resolution neural networks represent both weights and activations with few bits, drastically reducing the multiplication complexity. Nonetheless, these products are accumulated using high-resolution (typically 32-bit) additions, an operation that dominates the arithmetic complexity of inference when using extreme quantization (e.g., binary weights). To further optimize inference, we propose a method that adapts neural networks to use low-resolution (8-bit) additions in the accumulators, achieving classification accuracy comparable to their 32-bit counterparts. We achieve resilience to low-resolution accumulation by inserting a cyclic activation layer, as well as an overflow penalty regularizer. We demonstrate the efficacy of our approach on both software and hardware platforms.