English

Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse

Machine Learning 2026-05-13 v2

Abstract

While many approaches to improve VQ-VAE performance focus on codebook size and utilization, the effect of dimensional collapse, where trained VQ-VAE representations live in an extremely low-dimensional subspace (1-2% of full rank), remains unaddressed. We show theoretically and empirically that dimension collapse causes a hard loss lower bound that various codebook improvement techniques fail to surpass. Our analytic framework extends the sequential learning effect of Saxe et al. [2014] by introducing ideas from rate-distortion theory and explains how the latent collapse is caused by the VQ suppressing lower-variance directions. Our theory justifies a simple solution: a "warm-up phase" that trains the model as an (unquantized) autoencoder before introducing VQ. On both synthetic experiments and large-scale image (VQGAN) and audio (WavTokenizer) VQ-VAEs, we show that AE Warm-Up successfully restores representation dimension, leading to lower reconstruction and perceptual loss at the same training budget. Across codebook sizes KK \in {210,214,2162^{10}, 2^{14}, 2^{16}}, AE warm-up raises VQGAN codebook effective dimension from 3-5 to 17-19 and reduces rFID by 17-35%; on WavTokenizer at KK \in {213,2142^{13}, 2^{14}}, it raises codebook dimension from 4 to 17-19 and improves PESQ by 11-14%. We empirically characterize how warm-up duration governs the achievable final loss. In agreement with experiment, our theoretical analysis predicts downstream performance as a function of warm-up length, enabling an adaptive criterion for switching from AE Warm-up to VQ-VAE training.

Keywords

Cite

@article{arxiv.2605.06870,
  title  = {Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse},
  author = {Xinyu Zhao and Nikita Karagodin and Hamed Hassani and Sinan Hersek and Paul Pu Liang and Yury Polyanskiy},
  journal= {arXiv preprint arXiv:2605.06870},
  year   = {2026}
}
R2 v1 2026-07-01T12:56:07.761Z