Sparse Bayesian Generative Modeling for Joint Parameter and Channel Estimation
Leveraging the inherent connection between sensing systems and wireless communications can improve their overall performance and is the core objective of joint communications and sensing. For effective communications, one has to frequently estimate the channel. Sensing, on the other hand, infers properties of the environment mostly based on estimated physical channel parameters, such as directions of arrival or delays. This work presents a low-complexity generative modeling approach that simultaneously estimates the wireless channel and its physical parameters without additional computational overhead. To this end, we leverage a recently proposed physics-informed generative model for wireless channels based on sparse Bayesian generative modeling and exploit the feature of conditionally Gaussian generative models to approximate the conditional mean estimator.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Sparse Bayesian Generative Modeling for Compressive Sensing
This work addresses the fundamental linear inverse problem in compressive sensing (CS) by introducing a new type of regularizing generative prior. Our proposed method utilizes ideas from classical dictionary-based CS and…
Compressive SensingUncertainty QuantificationVariational InferenceFully Bayesian Autoencoders with Latent Sparse Gaussian Processes
Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the learned representations are i.i.d. and f…
Gaussian ProcessesRepresentation LearningLeveraging joint sparsity in hierarchical Bayesian learning
We present a hierarchical Bayesian learning approach to infer jointly sparse parameter vectors from multiple measurement vectors. Our model uses separate conditionally Gaussian priors for each parameter vector and common…
Bayesian InferencePhysics-Informed Generative Modeling of Wireless Channels
Learning the site-specific distribution of the wireless channel within a particular environment of interest is essential to exploit the full potential of machine learning (ML) for wireless communications and radar applic…
BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning
While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid design limits representational flexibility and often results in overconf…
parameter-efficient fine-tuningTopic Models