REVIEW 2 cited by
VAE Approximation Error: ELBO and Exponential Families
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The importance of Variational Autoencoders reaches far beyond standalone generative models -- the approach is also used for learning latent representations and can be generalized to semi-supervised learning. This requires a thorough analysis of their commonly known shortcomings: posterior collapse and approximation errors. This paper analyzes VAE approximation errors caused by the combination of the ELBO objective and encoder models from conditional exponential families, including, but not limited to, commonly used conditionally independent discrete and continuous models. We characterize subclasses of generative models consistent with these encoder families. We show that the ELBO optimizer is pulled away from the likelihood optimizer towards the consistent subset and study this effect experimentally. Importantly, this subset can not be enlarged, and the respective error cannot be decreased, by considering deeper encoder/decoder networks.
Forward citations
Cited by 2 Pith papers
-
Inverse Design of Metamaterials with Manufacturing-Guiding Spectrum-to-Structure Conditional Diffusion Model
A conditional diffusion model generates diverse, manufacturable free-form metamaterial designs from a target spectrum, demonstrated by a fabricated thermal camouflage emitter.
-
Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
The authors derive information-theoretic generalization bounds for VAEs and diffusion models that expose a trade-off in the diffusion time T, and propose using the computable bound to select T and regularize training.
Discussion (0). Continue with ORCID to comment.