mlsanityData to 7 Oct 2026

Adaptive Heterogeneous Mixtures of Normalising Flows for Robust Variational Inference

arXiv 2510.02056 ↗First posted 2 Oct 2025cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Normalising-flow variational inference (VI) can approximate complex posteriors, yet single-flow models often behave inconsistently across qualitatively different distributions. We propose Adaptive Mixture Flow Variational Inference (AMF-VI), a heterogeneous mixture of complementary flows (MAF, RealNVP, RBIG) trained in two stages: (i) sequential expert training of individual flows, and (ii) adaptive global weight estimation via likelihood-driven updates, without per-sample gating or architectural changes. Evaluated on six canonical posterior families of banana, X-shape, two-moons, rings, a bimodal, and a five-mode mixture, AMF-VI achieves consistently lower negative log-likelihood than each single-flow baseline and delivers stable gains in transport metrics (Wasserstein-2) and maximum mean discrepancy (MDD), indicating improved robustness across shapes and modalities. The procedure is efficient and architecture-agnostic, incurring minimal overhead relative to standard flow training, and demonstrates that adaptive mixtures of diverse flows provide a reliable route to robust VI across diverse posterior families whilst preserving each expert's inductive bias.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

21 of 35 references.

References · 21

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2016Variational Inference: A Review for Statisticianscited by 1,466
  8. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  9. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  10. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  11. 2018Invertible Residual Networkscited by 364
  12. 2017VAE with a VampPriorcited by 247
9 more
  1. 2016Mode Regularized Generative Adversarial Networkscited by 123
  2. 2019Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Predictioncited by 96
  3. 2019Semi-Supervised Learning with Normalizing Flowscited by 76
  4. 2018Sylvester Normalizing Flows for Variational Inferencecited by 71
  5. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  6. 2019The continuous Bernoulli: fixing a pervasive error in variational autoencoderscited by 40
  7. 2016Iterative Gaussianization: from ICA to Random Rotationscited by 26
  8. 2018Variational Inference with Tail-adaptive f-Divergencecited by 25
  9. 2020Variational Mixture of Normalizing Flowscited by 15

Built on by

Not cited yet.