AI RESEARCH
Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse
arXiv CS.LG
•
ArXi:2605.06870v1 Announce Type: new 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 by.