SAHMM-VAE: A Source-Wise Adaptive Hidden Markov Prior Variational Autoencoder for Unsupervised Blind Source Separation

• URL: http://arxiv.org/abs/2603.25776v1
• Date: Thu, 26 Mar 2026 13:08:16 GMT
• Title: SAHMM-VAE: A Source-Wise Adaptive Hidden Markov Prior Variational Autoencoder for Unsupervised Blind Source Separation
• Abstract summary: SAHMM-VAE is a source-wise adaptive Hidden Markov prior variational autoencoder for unsupervised blind source separation.<n>We develop three branches within one common framework: a Gaussian-emission HMM prior, a Markov-switching autoregressive HMM prior, and an HMM state-flow prior with state-wise autoregressive flow transformations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose SAHMM-VAE, a source-wise adaptive Hidden Markov prior variational autoencoder for unsupervised blind source separation. Instead of treating the latent prior as a single generic regularizer, the proposed framework assigns each latent dimension its own adaptive regime-switching prior, so that different latent dimensions are pulled toward different source-specific temporal organizations during training. Under this formulation, source separation is not implemented as an external post-processing step; it is embedded directly into variational learning itself. The encoder, decoder, posterior parameters, and source-wise prior parameters are optimized jointly, where the encoder progressively learns an inference map that behaves like an approximate inverse of the mixing transformation, while the decoder plays the role of the generative mixing model. Through this coupled optimization, the gradual alignment between posterior source trajectories and heterogeneous HMM priors becomes the mechanism through which different latent dimensions separate into different source components. To instantiate this idea, we develop three branches within one common framework: a Gaussian-emission HMM prior, a Markov-switching autoregressive HMM prior, and an HMM state-flow prior with state-wise autoregressive flow transformations. Experiments show that the proposed framework achieves unsupervised source recovery while also learning meaningful source-wise switching structures. More broadly, the method extends our structured-prior VAE line from smooth, mixture-based, and flow-based latent priors to adaptive switching priors, and provides a useful basis for future work on interpretable and potentially identifiable latent source modeling.

Related papers

• From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation [108.02425846269234]
  controllable image generation has made significant strides by incorporating visual reference conditions.<n>Existing methods predominantly operate as open-loop systems.<n>We propose a novel test-time iterative optimization framework that reformulates reference-consistent generation as a closed-loop dynamic tracking problem.
  arXiv  Detail & Related papers  (2026-07-06T05:36:30Z)
• Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection [41.96735569500412]
  Open-set supervised anomaly detection (OSAD) aims to identify unseen anomalies using limited anomalous supervision.<n>We propose a framework that learns a continuous transformation from normal feature distributions to a structured Gaussian mixture prototype space.<n>MPFM achieves state-of-the-art performance across diverse benchmarks under both single- and multi-anomaly settings.
  arXiv  Detail & Related papers  (2026-05-04T10:36:43Z)
• StrADiff: A Structured Source-Wise Adaptive Diffusion Framework for Linear and Nonlinear Blind Source Separation [0.0]
  This paper presents a Structured Source-Wise Adaptive Diffusion Framework for linear and nonlinear blind source separation.<n>The framework interprets each latent dimension as a source component and assigns to it an individual adaptive diffusion mechanism.<n>It learns source recovery and the mixing/reconstruction process jointly within a unified end-to-end objective.
  arXiv  Detail & Related papers  (2026-04-04T14:47:06Z)
• PDGMM-VAE: A Variational Autoencoder with Adaptive Per-Dimension Gaussian Mixture Model Priors for Nonlinear ICA [1.7403133838762448]
  Independent component analysis is a core framework within blind source separation.<n>We propose PDGMM-VAE, a source-oriented variational autoencoder in which each latent dimension, interpreted explicitly as an individual source signal, is assigned its own Gaussian mixture model prior.<n> Experimental results on both linear and nonlinear mixing problems demonstrate that PDGMM-VAE can recover latent source signals.
  arXiv  Detail & Related papers  (2026-03-20T08:54:35Z)
• AR-Flow VAE: A Structured Autoregressive Flow Prior Variational Autoencoder for Unsupervised Blind Source Separation [1.4174475093445233]
  We propose AR-Flow VAE, a novel VAE-based framework for blind source separation.<n>This work provides a foundation for future investigations into the identifiability and interpretability of AR-Flow VAE.
  arXiv  Detail & Related papers  (2026-03-15T15:35:51Z)
• Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection [58.25418970608328]
  Single-Domain Generalized Object Detection (Single-DGOD) aims to transfer a detector trained on one source domain to multiple unknown domains.<n>Existing methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity.<n>We propose a new method, which simulates the progressive evolution of features from the source domain to simulated latent distributions.
  arXiv  Detail & Related papers  (2025-11-13T03:10:39Z)
• Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition [64.37805399216347]
  Personalized facial expression recognition (FER) involves adapting a machine learning model using samples from labeled sources and unlabeled target domains.<n>We propose a progressive MSDA approach that gradually introduces information from subjects based on their similarity to the target subject.
  arXiv  Detail & Related papers  (2025-04-05T19:14:51Z)
• Heterogenous Multi-Source Data Fusion Through Input Mapping and Latent Variable Gaussian Process [8.32027826756131]
  The proposed framework is demonstrated and analyzed on three engineering case studies. It provides improved predictive accuracy over a single source model and transformed but source unaware model.
  arXiv  Detail & Related papers  (2024-07-15T22:27:04Z)
• Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation [70.2283756542824]
  Dior-CVAE is a hierarchical conditional variational autoencoder (CVAE) with diffusion priors to address these challenges. We employ a diffusion model to increase the complexity of the prior distribution and its compatibility with the distributions produced by a PLM. Experiments across two commonly used open-domain dialog datasets show that our method can generate more diverse responses without large-scale dialog pre-training.
  arXiv  Detail & Related papers  (2023-05-24T11:06:52Z)
• SIReN-VAE: Leveraging Flows and Amortized Inference for Bayesian Networks [2.8597160727750564]
  This work explores incorporating arbitrary dependency structures, as specified by Bayesian networks, into VAEs. This is achieved by extending both the prior and inference network with graphical residual flows. We compare our model's performance on several synthetic datasets and show its potential in data-sparse settings.
  arXiv  Detail & Related papers  (2022-04-23T10:31:08Z)
• Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation [78.38321096371106]
  Prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios demanding source-free adaptation. In this work, we enable source-free DA by partitioning the task into two: a) source-only domain generalization and b) source-free target adaptation. We introduce a novel conditional prior-enforcing auto-encoder that discourages spatial irregularities, thereby enhancing the pseudo-label quality.
  arXiv  Detail & Related papers  (2021-08-25T14:18:59Z)
• Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
  Variational autoencoders (VAE) are a powerful and widely-used class of generative models. We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
  arXiv  Detail & Related papers  (2021-01-06T17:36:26Z)
• On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond [82.18770740564642]
  Variational autoencoders (VAEs) combine latent variables with amortized variational inference. We observe the encoder-decoder incompatibility that leads to poor parameterizations of the data manifold. We propose Coupled-VAE, which couples a VAE model with a deterministic autoencoder with the same structure.
  arXiv  Detail & Related papers  (2020-04-20T10:34:10Z)

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.