Stick-Breaking Mixture Normalizing Flows with Component-Wise Tail Adaptation for Variational Inference

• URL: http://arxiv.org/abs/2510.07965v1
• Date: Thu, 09 Oct 2025 08:57:27 GMT
• Title: Stick-Breaking Mixture Normalizing Flows with Component-Wise Tail Adaptation for Variational Inference
• Authors: Seungsu Han, Juyoung Hwang, Won Chang,
• Abstract summary: We propose a stick-breaking mixture base with component-wise tail adaptation (StiCTAF) for posterior approximation.<n>Experiments on synthetic posteriors demonstrate improved tail recovery and better coverage of multiple modes compared to benchmark models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Normalizing flows with a Gaussian base provide a computationally efficient way to approximate posterior distributions in Bayesian inference, but they often struggle to capture complex posteriors with multimodality and heavy tails. We propose a stick-breaking mixture base with component-wise tail adaptation (StiCTAF) for posterior approximation. The method first learns a flexible mixture base to mitigate the mode-seeking bias of reverse KL divergence through a weighted average of component-wise ELBOs. It then estimates local tail indices of unnormalized densities and finally refines each mixture component using a shared backbone combined with component-specific tail transforms calibrated by the estimated indices. This design enables accurate mode coverage and anisotropic tail modeling while retaining exact density evaluation and stable optimization. Experiments on synthetic posteriors demonstrate improved tail recovery and better coverage of multiple modes compared to benchmark models. We also present a real-data analysis illustrating the practical benefits of our approach for posterior inference.

Related papers

• Bayesian Signal Component Decomposition via Diffusion-within-Gibbs Sampling [63.87118366026116]
  In signal processing, the estimation of components of interest is a crucial pre-processing step.<n>We develop a framework for a signal component decomposition, which combines Gibbs sampling with plug-and-play ( plug-and-play ( DiG)<n>We show that DiG can be interpreted as an extension of a class recently proposed diffusion-based samplers, and that, for suitable classes of sensing operators, DiG better exploits the structure of the measurement structure.
  arXiv  Detail & Related papers  (2026-02-11T12:34:37Z)
• End-To-End Learning of Gaussian Mixture Priors for Diffusion Sampler [15.372235873766812]
  Learnable mixture priors offer improved control over exploration, adaptability to target support, and increased to counteract mode collapse.<n>Our experimental results demonstrate significant performance improvements across a diverse range of real-world and synthetic benchmark problems.
  arXiv  Detail & Related papers  (2025-03-01T14:58:14Z)
• Fast sampling and model selection for Bayesian mixture models [3.198144010381572]
  We argue in favor of fitting the marginal posterior distribution over component assignments directly, rather than Gibbs sampling from the joint posterior.<n>We describe a new Monte Carlo algorithm for sampling from the marginal posterior of a general integrable mixture.<n>We demonstrate the approach with a selection of applications to Gaussian, Poisson, and categorical models.
  arXiv  Detail & Related papers  (2025-01-13T19:58:37Z)
• Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance [52.093434664236014]
  Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. Inspired by this finding, we propose to improve recent methods by using more principled covariance determined by maximum likelihood estimation.
  arXiv  Detail & Related papers  (2024-02-03T13:35:39Z)
• Entropy-MCMC: Sampling from Flat Basins with Ease [10.764160559530849]
  We introduce an auxiliary guiding variable, the stationary distribution of which resembles a smoothed posterior free from sharp modes, to lead the MCMC sampler to flat basins. By integrating this guiding variable with the model parameter, we create a simple joint distribution that enables efficient sampling with minimal computational overhead. Empirical results demonstrate that our method can successfully sample from flat basins of the posterior, and outperforms all compared baselines on multiple benchmarks.
  arXiv  Detail & Related papers  (2023-10-09T04:40:20Z)
• Ensemble Modeling for Multimodal Visual Action Recognition [50.38638300332429]
  We propose an ensemble modeling approach for multimodal action recognition. We independently train individual modality models using a variant of focal loss tailored to handle the long-tailed distribution of the MECCANO [21] dataset.
  arXiv  Detail & Related papers  (2023-08-10T08:43:20Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flows [53.32246823168763]
  Fat-tailed densities commonly arise as posterior and marginal distributions in robust models and scale mixtures. We first improve previous theory on tails of Lipschitz flows by quantifying how tails affect the rate of tail decay. We then develop an alternative theory for tail parameters which is sensitive to tail-anisotropy.
  arXiv  Detail & Related papers  (2022-05-16T18:03:41Z)
• Natural Gradient Variational Inference with Gaussian Mixture Models [1.7948767405202701]
  Variational Inference (VI) methods approximate the posterior with a distribution usually chosen from a simple family using optimization. The main contribution of this work is described is a set of update rules for natural gradient variational inference with mixture of Gaussians.
  arXiv  Detail & Related papers  (2021-11-15T20:04:32Z)
• Model Fusion with Kullback--Leibler Divergence [58.20269014662046]
  We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors.
  arXiv  Detail & Related papers  (2020-07-13T03:27:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.