analiza aiqbench
BayesNDE advances neural density estimation by leveraging Bayesian generative modeling to eliminate the need for invertible networks or Jacobian computations, offering a more flexible approach to capturing complex data structures. This method improves upon state-of-the-art estimators in both synthetic and real-world scenarios, particularly enhancing anomaly detection capabilities through adaptive posterior inference. The work represents a significant methodological step forward in machine learning, enabling generative models to serve directly as robust density estimation tools without restrictive architectural constraints.
BayesNDE: Bayesian Generative Modeling for Neural Density Estimation
arXiv:2609.39843v1 Announce Type: cross Abstract: Density estimation is a fundamental problem in statistics and machine learning. In this work, we introduce BayesNDE, a neural density estimator based on Bayesian generative modeling. BayesNDE learns a Bayesian generative model and evaluates its density without requiring invertible networks or Jacobian-determinant computation. For each observation, it infers a sample-specific latent posterior to construct an adaptive proposal that focuses computation on regions contributing most to its density. Bridge sampling then combines samples from this proposal with separate posterior samples to estimate the density. Experiments on nonlinear and multimodal synthetic datasets show improved estimation of density values and better recovery of the density structure compared to the state-of-the-art neural density estimators. Applications to real-world datasets further demonstrate improved anomaly detection. Together, these results highlight BayesNDE as a flexible and effective neural density estimator, demonstrating how posterior inference can turn generative models into tools for density estimation. The code and tutorials are available at https://github.com/liuq-lab/BayesNDE.
Abstract:Density estimation is a fundamental problem in statistics and machine learning. In this work, we introduce BayesNDE, a neural density estimator based on Bayesian generative modeling. BayesNDE learns a Bayesian generative model and evaluates its density without requiring invertible networks or Jacobian-determinant computation. For each observation, it infers a sample-specific latent posterior to construct an adaptive proposal that focuses computation on regions contributing most to its density. Bridge sampling then combines samples from this proposal with separate posterior samples to estimate the density. Experiments on nonlinear and multimodal synthetic datasets show improved estimation of density values and better recovery of the density structure compared to the state-of-the-art neural density estimators. Applications to real-world datasets further demonstrate improved anomaly detection. Together, these results highlight BayesNDE as a flexible and effective neural density estimator, demonstrating how posterior inference can turn generative models into tools for density estimation. The code and tutorials are available at this https URL.
Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Methodology (stat.ME)
arXiv:2609.39843 [stat.ML]
(or arXiv:2609.39843v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2609.39843 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 257 cuvinte
Subiecte conexe
DiScoFormer: Plug-In Density and Score Estimation with Transformers
arXiv · 5 iun. 2026
DiScoFormer: One transformer for density and score, across distributions
Hugging Face · 29 iun. 2026
Generative Modeling: A Review
arXiv · 27 aug. 2026
Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Exactly Detection Tasks
arXiv · 27 aug. 2026