DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
Mohammad Hassan Vali, Tom Bäckström, Arno Solin
Abstract
Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping the forward pass hard while letting gradients flow. We also present a space-filling variant (SF-DiVeQ) that assigns to a curve constructed by the lines connecting codewords, resulting in less quantization error and full codebook usage. Both methods train end-to-end without requiring auxiliary losses or temperature schedules. On VQ-VAE compression and VQGAN generation across various data sets, they improve reconstruction and sample quality over alternative quantization approaches.
BibTeX
@inproceedings{
vali2026diveq,
title={DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick},
author={Mohammad Hassan Vali and Tom B{\"a}ckstr{\"o}m and Arno Solin},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=KRVnpTbx7R}
}