Unrolling Particles: Unsupervised Learning of Sampling Distributions

Gama, Fernando; Zilberstein, Nicolas; Baraniuk, Richard G.; Segarra, Santiago

doi:10.1109/icassp43922.2022.9747290

Cited by 7 publications

(4 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Proposal Distributionsmentioning

confidence: 99%

“…Different ways to learn proposal distributions in differentiable particle filters have been proposed [50,95,96]. In [95,96], the proposal distribution is constructed as a Gaussian distribution whose mean and covariance matrix are given by a neural network with the estimate of the previous latent state and the current observation as inputs. To provide a mechanism for constructing proposal distributions more flexible than Gaussian distributions, it was proposed in [50] to construct proposal distributions for differentiable particle filters with conditional normalising flows [97].…”

Section: Proposal Distributionsmentioning

confidence: 99%

See 1 more Smart Citation

An overview of differentiable particle filters for data-adaptive sequential Bayesian inference

Chen,

2023

FoDS

View full text Add to dashboard Cite

By approximating posterior distributions with weighted samples, particle filters (PFs) provide an efficient mechanism for solving non-linear sequential state estimation problems. While the effectiveness of particle filters has been recognised in various applications, their performance relies on the knowledge of dynamic models and measurement models, as well as the construction of effective proposal distributions. An emerging trend involves constructing components of particle filters using neural networks and optimising them by gradient descent, and such data-adaptive particle filtering approaches are often called differentiable particle filters. Due to the expressiveness of neural networks, differentiable particle filters are a promising computational tool for performing inference on sequential data in complex, high-dimensional tasks, such as vision-based robot localisation. In this paper, we review recent advances in differentiable particle filters and their applications. We place special emphasis on different design choices for key components of differentiable particle filters, including dynamic models, measurement models, proposal distributions, optimisation objectives, and differentiable resampling techniques.

show abstract

Section: Proposal Distributionsmentioning

confidence: 99%

Section: Proposal Distributionsmentioning

confidence: 99%

An overview of differentiable particle filters for data-adaptive sequential Bayesian inference

Chen,

2023

FoDS

View full text Add to dashboard Cite

show abstract

“…Algorithm unfolding decouples the update steps of an iterative algorithm to create a cascade of hybrid layers that preserve the original update structure but introduces one or more learnable parameters from data. This form of domain-inspired learning has been extremely popular and effective in several application areas, including but not limited to non-negative matrix factorization [29], iterative soft thresholding [30], semantic image segmentation [31], blind deblurring [32], clutter suppression [33], particle filtering [34], symbol detection [35], link scheduling [36], energy-aware power allocation [37], and beamforming in wireless networks [21]- [23]. These algorithms use various neural layers to learn one or more parameters of the iterative algorithm being unfolded or to approximate certain computational steps in the algorithm to reduce complexity and speed-up processing.…”

Section: Introductionmentioning

confidence: 99%

Unfolding WMMSE Using Graph Neural Networks for Efficient Power Allocation

Chowdhury

Verma

Rao

et al. 2021

IEEE Trans. Wireless Commun.

117

View full text Add to dashboard Cite

We develop an efficient and near-optimal solution for beamforming in multi-user multiple-input-multiple-output single-hop wireless ad-hoc interference networks. Inspired by the weighted minimum mean squared error (WMMSE) method, a classical approach to solving this problem, and the principle of algorithm unfolding, we present unfolded WMMSE (UWMMSE) for MU-MIMO. This method learns a parameterized functional transformation of key WMMSE parameters using graph neural networks (GNNs), where the channel and interference components of a wireless network constitute the underlying graph. These GNNs are trained through gradient descent on a network utility metric using multiple instances of the beamforming problem. Comprehensive experimental analyses illustrate the superiority of UWMMSE over the classical WMMSE and stateof-the-art learning-based methods in terms of performance, generalizability, and robustness.

show abstract

“…On the other hand, it is also necessary to mention that before prediction, the ANN should firstly be trained [38]. The training could be with or without the supervisor and classified into supervised [39], semi-supervised [40] and unsupervised networks [41]. It depends on the type of the network and training dataset [42].…”

Section: Introductionmentioning

confidence: 99%

Trends of Microwave Devices Design Based on Artificial Neural Networks: A Review

et al. 2022

View full text Add to dashboard Cite

The usage of techniques of the artificial neural networks (ANNs) in the field of microwave devices has recently increased. The advantages of ANNs in comparison with traditional full-wave methods are that the prediction speed when the traditional time-consuming iterative calculations are not required and also the complex mathematical model of the microwave device is no longer needed. Therefore, the design of microwave device could be repeated many times in real time. However, methods of artificial neural networks still lag behind traditional full-wave methods in terms of accuracy. The prediction accuracy depends on the structure of the selected neural network and also on the obtained dataset for the training of the network. Therefore, the paper presents a systematic review of the implementation of ANNs in the field of the design and analysis of microwave devices. The guidelines for the systematic literature review and the systematic mapping research procedure, as well as the Preferred Report Items for Systematic Reviews and Meta-Analysis statements (PRISMA) are used to conduct literature search and report the results. The goal of the paper is to summarize the application areas of usage of ANNs in the field of microwave devices, the type and structure of the used artificial neural networks, the type and size of the dataset, the interpolation and the augmentation of the training dataset, the training algorithm and training errors and also to discuss the future perspectives of the usage of ANNs in the field of microwave devices.

show abstract

Unrolling Particles: Unsupervised Learning of Sampling Distributions

Cited by 7 publications

References 65 publications

An overview of differentiable particle filters for data-adaptive sequential Bayesian inference

An overview of differentiable particle filters for data-adaptive sequential Bayesian inference

Unfolding WMMSE Using Graph Neural Networks for Efficient Power Allocation

Trends of Microwave Devices Design Based on Artificial Neural Networks: A Review

Contact Info

Product

Resources

About