Integrating a trained diffusion denoiser into joint decoding yields a strictly tighter random-coding achievable bound for finite blocklength unsourced multiple access, with simulations showing at least 0.5 dB Eb/N0 improvement.
We rewrite the error event as a union ofF(S 0, S′ 0)to have P[t-misdecoded]≤P [ S0∈( Ka t ) [ S′ 0∈( M−K a t ) F(S 0, S′ 0)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diffusion Denoiser Achievable Analysis for Finite Blocklength Unsourced Random Access
Integrating a trained diffusion denoiser into joint decoding yields a strictly tighter random-coding achievable bound for finite blocklength unsourced multiple access, with simulations showing at least 0.5 dB Eb/N0 improvement.