VAE의 중요한 하이퍼파라미터인 beta와 sigma가 수식적으로 독특한 관계를 가지고 있기 때문에, 양쪽에서 최적을 얻으려면 특정한 구조의 loss를 사용해야 한다는 내용입니다.

[arxiv]
https://www.arxiv.org/abs/2409.09361

[abstract]
Variational autoencoder (VAE) is an established generative model but is notorious for its blurriness. In this work, we investigate the blurry output problem of VAE and resolve it, exploiting the variance of Gaussian decoder and β of beta-VAE [14]. Specifically, we reveal that the indistinguishability of decoder variance and β hinders appropriate analysis of the model by random likelihood value, and limits performance improvement by omitting the gain from
β. To address the problem, we propose Beta-Sigma VAE (BS-VAE) that explicitly separates β and decoder variance σ_x^2 in the model. Our method demonstrates not only superior performance in natural image synthesis but also controllable parameters and predictable analysis compared to conventional VAE. In our experimental evaluation, we employ the analysis of rate-distortion curve and proxy metrics on computer vision datasets. The code is available on https://github.com/overnap/BS-VAE.