AI RESEARCH
Instance-Adaptive Parametrization for Amortized Variational Inference
arXiv CS.LG
•
ArXi:2604.06796v1 Announce Type: new Latent variable models, including variational autoencoders (VAE), remain a central tool in modern deep generative modeling due to their scalability and a well-founded probabilistic formulation. These models rely on amortized variational inference to enable efficient posterior approximation, but this efficiency comes at the cost of a shared parametrization, giving rise to the amortization gap.