ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generation
ELVAE places an input-dependent normal--inverse-gamma (NIG) hierarchy at each VAE latent coordinate, separating location uncertainty $u_{\mathrm{epi}}=β/[ν(α-1)]$ from conditional variability $u_{\mathrm{var}}=β/(α-1)$. The marginalized latent law, however, identifies only the three quotient coordinates $(γ,α,c)$ with $c=β(1+1/ν)$; reconstruction is blind to one $(ν,β)$ fiber direction. A companion theoretical analysis shows that the complete NIG prior and forward KL select a unique prior-relative canonical representative on each fiber, so canonical inverse allocation is not a fourth independent information channel. Empirically, trained inverse evidence $1/ν$ remains the strongest sensiti...
| Authors | Ge Wang |
|---|---|
| Primary category | cs.LG |
| Published | 11 August 2026 |
| Last updated at source | 20 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.