# The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's Algorithm

arXiv: https://arxiv.org/abs/2508.01077 · HTML: https://mlsanity.com/paper/2508.01077/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 9 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Builds on (most cited first, 4 of 4)

- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization](https://mlsanity.com/paper/2505.11695/) (2025)
- [The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm](https://mlsanity.com/paper/2507.18553/) (2025)

## Built on by (most cited first, 9 of 9)

- [WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization](https://mlsanity.com/paper/2603.04956/) (2026)
- [High-Rate Quantized Matrix Multiplication II](https://mlsanity.com/paper/2605.13768/) (2026)
- [GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding](https://mlsanity.com/paper/2607.27042/) (2026)
- [Price of metric universality in vector quantization is at most 0.11 bit](https://mlsanity.com/paper/2602.05790/) (2026)
- [FastKron: Efficient Quantization with Kronecker-Factored Hessians](https://mlsanity.com/paper/2608.06291/) (2026)
- [WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians](https://mlsanity.com/paper/2609.14706/) (2026)
- [Generalization behavior of OPTQ and the role of regularization](https://mlsanity.com/paper/2609.31560/) (2026)
- [Product-Aware Deterministic Rounding for Quantized Matrix Multiplication](https://mlsanity.com/paper/2609.31641/) (2026)
- [Revisiting Error Feedback for Model Quantization](https://mlsanity.com/paper/2610.18139/) (2026)

## Abstract (arXiv)

We explain how data-driven quantization of a linear unit in a neural network corresponds to solving the closest vector problem for a certain lattice generated by input data. We prove that the GPTQ algorithm is equivalent to Babai's well-known nearest-plane algorithm. We furthermore provide geometric intuition for both algorithms. Lastly, we note the consequences of these results, in particular hinting at the possibility of using lattice basis reduction for improved quantization.