mlsanityData to 7 Oct 2026

Inference and Sampling for Archimax Copulas

arXiv 2205.14025 ↗First posted 27 May 2022stat.ME cs.LG stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Understanding multivariate dependencies in both the bulk and the tails of a distribution is an important problem for many applications, such as ensuring algorithms are robust to observations that are infrequent but have devastating effects. Archimax copulas are a family of distributions endowed with a precise representation that allows simultaneous modeling of the bulk and the tails of a distribution. Rather than separating the two as is typically done in practice, incorporating additional information from the bulk may improve inference of the tails, where observations are limited. Building on the stochastic representation of Archimax copulas, we develop a non-parametric inference method and sampling algorithm. Our proposed methods, to the best of our knowledge, are the first that allow for highly flexible and scalable inference and sampling algorithms, enabling the increased use of Archimax copulas in practical settings. We experimentally compare to state-of-the-art density modeling techniques, and the results suggest that the proposed method effectively extrapolates to the tails while scaling to higher dimensional data. Our findings suggest that the proposed algorithms can be used in a variety of applications where understanding the interplay between the bulk and the tails of a distribution is necessary, such as healthcare and safety.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 31 of its 121 references that are in the map. First posted on arXiv 27 May 2022.

Builds on

31 of 121 references.

References · 31

  1. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  2. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  3. 2017Generative Adversarial Networks: An Overviewcited by 588
  4. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 147
  5. 2020COPOD: Copula-Based Outlier Detectioncited by 143
  6. 2020Perfect density models cannot guarantee anomaly detectioncited by 39
  7. 2022TACTiS: Transformer-Attentional Copulas for Time Seriescited by 38
  8. 2021Copula Flows for Synthetic Data Generationcited by 35
  9. 2018Autoregressive Quantile Networks for Generative Modelingcited by 31
  10. 2020ExGAN: Adversarial Generation of Extreme Samplescited by 28
  11. 2018Neural Likelihoods via Cumulative Distribution Functionscited by 25
  12. 2020Deep Archimedean Copulascited by 24
19 more
  1. 2019Copulas as High-Dimensional Generative Models: Vine Copula Autoencoderscited by 20
  2. 2019Deep Generative Quantile-Copula Models for Probabilistic Forecastingcited by 18
  3. 2021Implicit Generative Copulascited by 17
  4. 2021Multi-Agent Imitation Learning with Copulascited by 13
  5. 2015Variational Gaussian Copula Inferencecited by 12
  6. 2020Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copulacited by 10
  7. 2020CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networkscited by 10
  8. 2018Learning Sparse Latent Representations with the Deep Copula Information Bottleneckcited by 9
  9. 2013Semi-Supervised Domain Adaptation with Non-Parametric Copulascited by 8
  10. 2021Generative Archimedean Copulascited by 8
  11. 2020Robust Correction of Sampling Bias Using Cumulative Distribution Functionscited by 6
  12. 2021MIND: Inductive Mutual Information Estimation, A Convex Maximum-Entropy Copula Approachcited by 6
  13. 2021Copula-Based Normalizing Flowscited by 5
  14. 2019Copula-like Variational Inferencecited by 4
  15. 2021Modeling Extremes with d-max-decreasing Neural Networkscited by 4
  16. 2013Gaussian Process Vine Copulas for Multivariate Dependencecited by 3
  17. 2013Gaussian Process Conditional Copulas with Applications to Financial Time Seriescited by 3
  18. 2016On structure, family and parameter estimation of hierarchical Archimedean copulascited by 3
  19. 2013Speedy Model Selection (SMS) for Copula Modelscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 2.

5 papers.

  1. 2024Your copula is a classifier in disguise: classification-based copula density estimationcited by 8
  2. 2023Retrospective Uncertainties for Deep Models using Vine Copulascited by 7
  3. 2025Diffusion and Flow-based Copulas: Forgetting and Remembering Dependenciescited by 7
  4. 2025IGNIS: A Robust Neural Network Framework for Constrained Parameter Estimation in Archimedean Copulascited by 1
  5. 2024A Generative Approach to Quasi-Random Sampling from Copulas via Space-Filling Designscited by 0