# Quantaized Winograd/Toom-Cook Convolution for DNNs: Beyond Canonical Polynomials Base

arXiv: https://arxiv.org/abs/2004.11077 · HTML: https://mlsanity.com/paper/2004.11077/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2020.

## Built on by (most cited first, 3 of 3)

- [Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile](https://mlsanity.com/paper/2209.12982/) (2022)
- [Fast Convolution based on Winograd Minimum Filtering: Introduction and Development](https://mlsanity.com/paper/2111.00977/) (2021)
- [UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization](https://mlsanity.com/paper/2602.18758/) (2026)

## Abstract (arXiv)

The problem how to speed up the convolution computations in Deep Neural Networks is widely investigated in recent years. The Winograd convolution algorithm is a common used method that significantly reduces time consumption. However, it suffers from a problem with numerical accuracy particularly for lower precisions. In this paper we present the application of base change technique for quantized Winograd-aware training model. We show that we can train the 8 bit quantized network to nearly the same accuracy (up to 0.5% loss) for tested network (Resnet18) and dataset (CIFAR10) as for quantized direct convolution with few additional operations in pre/post transformations. Keeping Hadamard product on 9 bits allow us to obtain the same accuracy as for direct convolution.