English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Predicting fading channels is a classical problem with a vast array ofapplications, including as an enabler of artificial intelligence (AI)-basedproactive resource allocation for cellular networks. Under the assumption thatthe fading channel follows a stationary complex Gaussian process, as forRayleigh and Rician fading models, the optimal predictor is linear, and it canbe directly computed from the Doppler spectrum via standard linear minimum meansquared error (LMMSE) estimation. However, in practice, the Doppler spectrum isunknown, and the predictor has only access to a limited time series ofestimated channels. This paper proposes to leverage meta-learning in order tomitigate the requirements in terms of training data for channel fadingprediction. Specifically, it first develops an offline low-complexity solutionbased on linear filtering via a meta-trained quadratic regularization. Then, anonline method is proposed based on gradient descent and equilibrium propagation(EP). Numerical results demonstrate the advantages of the proposed approach,showing its capacity to approach the genie-aided LMMSE solution with a smallnumber of training data points.

Predicting Flat-Fading Channels via Meta-Learned Closed-Form Linear Filters and Equilibrium Propagation