# Boolean Logic as an Error feedback mechanism

arXiv: https://arxiv.org/abs/2401.16418 · HTML: https://mlsanity.com/paper/2401.16418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 8 of 8)

- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Error Feedback Fixes SignSGD and other Gradient Compression Schemes](https://mlsanity.com/paper/1901.09847/) (2019)
- [Training Quantized Nets: A Deeper Understanding](https://mlsanity.com/paper/1706.02379/) (2017)
- [Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats](https://mlsanity.com/paper/2112.10769/) (2021)
- [High-Accuracy Low-Precision Training](https://mlsanity.com/paper/1803.03383/) (2018)
- [Low-Precision Stochastic Gradient Langevin Dynamics](https://mlsanity.com/paper/2206.09909/) (2022)
- [AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks](https://mlsanity.com/paper/2211.03741/) (2022)
- [Boolean Variation and Boolean Logic BackPropagation](https://mlsanity.com/paper/2311.07427/) (2023)

## Abstract (arXiv)

The notion of Boolean logic backpropagation was introduced to build neural networks with weights and activations being Boolean numbers. Most of computations can be done with Boolean logic instead of real arithmetic, both during training and inference phases. But the underlying discrete optimization problem is NP-hard, and the Boolean logic has no guarantee. In this work we propose the first convergence analysis, under standard non-convex assumptions.