DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
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 input 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. In VQ-VAE image compression, VQGAN image generation, and DAC speech coding tasks across various data sets, our proposed methods improve reconstruction and sample quality over alternative quantization approaches.
Cite
Text
Vali et al. "DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick." International Conference on Learning Representations, 2026.Markdown
[Vali et al. "DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/vali2026iclr-diveq/)BibTeX
@inproceedings{vali2026iclr-diveq,
title = {{DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick}},
author = {Vali, Mohammad Hassan and Bäckström, Tom and Solin, Arno},
booktitle = {International Conference on Learning Representations},
year = {2026},
url = {https://mlanthology.org/iclr/2026/vali2026iclr-diveq/}
}