A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Learning How to Demodulate from Few Pilots via Meta-Learning
[article]
2019
arXiv
pre-print
Accordingly, pilots from previous IoT transmissions are used as meta-training in order to learn a demodulator that is able to quickly adapt to new end-to-end channel conditions from few pilots. ...
This paper proposes to tackle this problem using meta-learning. ...
Fig. 1 . 1 Illustration of few-pilot training for an IoT system via meta-learning.
Fig. 2 . 2 Illustration of meta-training and meta-test data for 4-PAM transmission from set S = {−3, −1, 1, 3}. ...
arXiv:1903.02184v1
fatcat:3fhuqz26fncx5d3b72ekrqhkyq
Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
[article]
2020
arXiv
pre-print
Accordingly, pilots from previous IoT transmissions are used as meta-training data in order to train a demodulator that is able to quickly adapt to new end-to-end channel conditions from few pilots. ...
VIA meta-learning (CAVIA). ...
is able to quickly adapt a demodulator to new end-to-end channel conditions from few pilots. ...
arXiv:1908.09049v3
fatcat:2nfbvcze4rghrgk5w5i32tehie
Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization
[article]
2022
arXiv
pre-print
Meta-learning processes pilot information from multiple frames in order to extract useful shared properties of effective demodulators across frames. ...
As a specific use case, the problems of demodulation and equalization over a fading channel based on the availability of few pilots are studied. ...
. • We introduce Bayesian meta-learning for the problems of demodulation and equalization from few pilots. ...
arXiv:2108.00785v3
fatcat:kn7grmfrv5hgjcewaxqnrr7hbq
Bayesian Active Meta-Learning for Reliable and Efficient AI-Based Demodulation
2022
Zenodo
Retrieved October 25, 2022, from https://doi.org/ 10.18742/rnvf-m076, and Rosalind (https://rosalind.kcl.ac.uk) ...
ACKNOWLEDGEMENT The authors would like to thank the use of the Research Computing Facility at King's College London (2022), King's Computational Research, Engineering and Technology Environment (CREATE ...
This paper has focused on the application of Bayesian meta-learning to the basic problems of demodulation/equalization from few pilots. ...
doi:10.5281/zenodo.7426620
fatcat:5vl3w3jhafb7rm3ypminrwfp3a
Learning with Limited Samples – Meta-Learning and Applications to Communication Systems
[article]
2022
arXiv
pre-print
To address labeled data scarcity, few-shot meta-learning optimizes learning algorithms that can efficiently adapt to new tasks quickly. ...
Then, we summarize known results on the generalization capabilities of meta-learning from a statistical learning viewpoint. ...
Fig. 1 : 1 Fig. 1: Illustration of few-pilot training for an IoT system via meta-learning.
1 arning 1 to Demodulate from Few Pilots via Offline and Online Meta-Learning Sangwoo Park, Student Member, ...
arXiv:2210.02515v1
fatcat:nhgobsuadveffakjbc5uxrjsky
A Channel Coding Benchmark for Meta-Learning
[article]
2021
arXiv
pre-print
Meta-learning provides a popular and effective family of methods for data-efficient learning of new tasks. However, several important issues in meta-learning have proven hard to study thus far. ...
For example, performance degrades in real-world settings where meta-learners must learn from a wide and potentially multi-modal distribution of training tasks; and when distribution shift exists between ...
Meta-learning is therefore a promising tool to enable rapid decoder adaptation with few pilot codes, as confirmed by early evidence [15] . ...
arXiv:2107.07579v3
fatcat:6uaeb4x2arhdbixhk2ktbhxn6q
RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes
[article]
2023
arXiv
pre-print
Furthermore, to address decoding under varying channel conditions, we propose agile meta-RELDEC (AM-RELDEC) that employs meta-reinforcement learning. ...
The main idea behind RELDEC is that an optimized decoding policy is subsequently obtained via reinforcement learning based on a Markov decision process (MDP). ...
Moreover, MAML has been used for channel coding based on few pilot transmission in [35] , where the focus is on learning a decoder for a fixed encoder via supervised learning. ...
arXiv:2112.13934v3
fatcat:me24ychb7bgtpnpq3ps27hbbxy
Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks
[article]
2022
arXiv
pre-print
While black-box meta-learning optimizes a general-purpose adaptation procedure via (stochastic) gradient descent, modular meta-learning finds a set of reusable modules that can form components of a solution ...
To this end, we propose a novel modular meta-learning technique that enables the efficient optimization of module assignment. ...
In particular, in [35] the authors use pilots from previous transmissions of Internet of Things (IoT) devices in order to adapt a demodulator to new channel conditions using few pilot symbols. ...
arXiv:2108.13178v2
fatcat:sh2eadjoa5cznoiq7t3gvw4zj4
An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning
[article]
2023
arXiv
pre-print
Prominent applications of BLO range from resource allocation for wireless systems to adversarial machine learning. ...
Recently, bi-level optimization (BLO) has taken center stage in some very exciting developments in the area of signal processing (SP) and machine learning (ML). ...
Consequently, we view this demodulation modeling as a few-shot meta-learning problem, aiming to derive a meta initialization from historical data that is able to quickly adapt to future devices. ...
arXiv:2308.00788v3
fatcat:sr6pbfxxxbeyjf3unefsoc37wq
Intelligent Radio Frequency Identification for URLLC in Industrial IoT Networks
2022
Symmetry
Semisupervised learning (SSL) can achieve remarkable identification accuracy by utilizing meta pseudo labels with few labeled samples and many unlabeled samples. ...
During the experimental process, we only selected few labeled samples, and the rest of the samples were selected to be unlabeled data to assist in the mutual learning of the two RFIResNets. ...
All authors have read and agreed to the published version of the manuscript.
Funding ...
doi:10.3390/sym14040801
dblp:journals/symmetry/ZhangRXR22
fatcat:kifpfnpjsrgb7fhkbeumvd7tsy
Predicting Bit Error Rate from Meta Information using Random Forests
[article]
2020
arXiv
pre-print
With the increasing power of machine learning-based reasoning, the use of meta-information (e.g., digital signal modulation parameters, channel conditions, etc.) to predict the performance of various signal ...
Specifically, RF used to predict the Bit-Error-Rate (BER) of all mitigation approaches so as to determine the approach with the best performance. ...
as pilot information is sufficient to learn channel conditions in an IoT scenario. ...
arXiv:2007.05503v1
fatcat:htvkamljsbblndzlutifalsnkq
Toward a 6G AI-Native Air Interface
[article]
2021
arXiv
pre-print
While it is clear that 6G must cater to the needs of large distributed learning systems, it is less certain if AI will play a defining role in the design of 6G itself. ...
The goal of this article is to paint a vision of a new air interface which is partially designed by AI to enable optimized communication schemes for any hardware, radio environment, and application. ...
Huttunen (and many others) for numerous discussions that helped to shape the vision outlined in this article. ...
arXiv:2012.08285v2
fatcat:ddcttujbyjdpjjsli24fq54jjy
Statistical Tools and Methodologies for URLLC – A Tutorial
[article]
2022
arXiv
pre-print
Finally, key research challenges and directions are highlighted to elucidate how URLLC analysis/design research may evolve in the coming years. ...
events simulation, v) large-scale tools such as stochastic geometry, clustering, compressed sensing, and mean-field games, vi) queuing theory and information freshness, and vii) machine learning. ...
Meta-learning based channel estimation and demodulation with few pilot symbols. The algorithm works by maximizing p(φ|θ) as in [186] . ...
arXiv:2212.03292v1
fatcat:kfa4sije6zdpdc45yu6yk263lm
Learning to Broadcast for Ultra-Reliable Communication with Differential Quality of Service via the Conditional Value at Risk
[article]
2021
arXiv
pre-print
Considering this theoretical result, meta-learning is introduced as a means to reduce sample complexity by leveraging data from previous deployments. ...
that achieved when the transmitter knows the fading distribution; and that meta-learning can significantly reduce data requirements. ...
Kang, “Learning to demodulate from few pilots via offline and online meta-
learning,” IEEE Trans. Signal Process., vol. 69, pp. 226–239, 2021.
[30] K. M. Cohen, S. Park, O. Simeone, and S. ...
arXiv:2112.02007v1
fatcat:5ubehnjmtfgc5g5han7lpl7cqa
Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues
[article]
2023
arXiv
pre-print
Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generations wireless systems. ...
In this context, domain generalization (DG) tackles the OOD-related issues by learning models on different and distinct source domains/datasets with generalization capabilities to unseen new domains without ...
from different scenarios, and iii) inability to quickly adapt to unseen scenarios, to name a few. ...
arXiv:2303.08106v1
fatcat:lwjoq7qrmfewnclxs3yoo3zt5i
« Previous
Showing results 1 — 15 out of 176 results