# Understanding Deep Generative Models with Generalized Empirical Likelihoods

Source: [Understanding Deep Generative Models with Generalized Empirical Likelihoods](<https://www.sota2.com/research/paper/68fa70391e209131cea49af2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T03:18:15.293Z

Authors: Suman Ravuri, M\\'elanie Rey, Shakir Mohamed, Marc Deisenroth

Published: 2023-06-16T11:33:47.000Z

## Abstract

Understanding how well a deep generative model captures a distribution of high-dimensional data remains an important open challenge. It is especially difficult for certain model classes, such as Generative Adversarial Networks and Diffusion Models, whose models do not admit exact likelihoods. In this work, we demonstrate that generalized empirical likelihood (GEL) methods offer a family of diagnostic tools that can identify many deficiencies of deep generative models (DGMs). We show, with appropriate specification of moment conditions, that the proposed method can identify which modes have been dropped, the degree to which DGMs are mode imbalanced, and whether DGMs sufficiently capture intra-class diversity. We show how to combine techniques from Maximum Mean Discrepancy and Generalized Empirical Likelihood to create not only distribution tests that retain per-sample interpretability, but also metrics that include label information. We find that such tests predict the degree of mode dropping and mode imbalance up to 60% better than metrics such as improved precision/recall. We provide an implementation at https://github.com/deepmind/understanding\_deep\_generative\_models\_with\_generalized\_empirical\_likelihood/.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Generative Modeling Evaluation on ImageNet 256x256](<https://www.sota2.com/research/sota/generative-modeling-evaluation-on-imagenet-256x256.md>): Generative Modeling Evaluation; ImageNet 256x256; KGEL2 ET: not recorded.

- [Generative Modeling Evaluation on ImageNet 256x256 (test)](<https://www.sota2.com/research/sota/generative-modeling-evaluation-on-imagenet-256x256-test.md>): Generative Modeling Evaluation; ImageNet 256x256 (test); KGEL ET Score: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.09780>)

[PDF](<https://arxiv.org/pdf/2306.09780.pdf>)

[Implementation](<https://github.com/deepmind/understanding_deep_generative_models_with_generalized_empirical_likelihood/>)