AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

Hee-Youl Kwak, Dae-Young Yun, Yongjune Kim, Sang-Hyo Kim, Jong-Seon No

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Train the post decoder on error-floor uncorrected words rather than unfiltered received wordsNMS decoder · WiMAX LDPC, error-floor samples at 4.5 dBTest FER: 0.315 times of the FER after base decodingImproved
Train the post decoder on uncorrected words from the waterfall region instead of the error-floor regionNMS decoder · WiMAX LDPC, waterfall samples at 3.5 dBTest FER: 0.77 times of the FER after base decodingNo clear effect
Train the post decoder on unfiltered received wordsNMS decoder · WiMAX LDPC, error-floor regionFERHurt
Add boosting with uncorrected words (ablation)NMS decoder · WiMAX LDPC, Eb/N0 5.0dBFER: 3.14×10^{-6} -> 2.77×10^{-7}Improved
Add block-wise training to boosting (ablation)NMS decoder · WiMAX LDPC, Eb/N0 5.0dBFER: 2.77×10^{-7} -> 1.84×10^{-7}Improved
Use proposed UCN/SCN weight sharing instead of full diversity weights (ablation)NMS decoder · WiMAX LDPC, Eb/N0 5.0dBFER: 1.84×10^{-7} -> 1.85×10^{-7}No clear effect
Use block-wise training with retraining rather than one-shot training (ablation)NMS decoder · WiMAX LDPC, post decoder, 50 iterationsTest FER: 0.18 -> 0.11Improved
Use block-wise training with retraining rather than iter-by-iter training (ablation)NMS decoder · WiMAX LDPC, post decoder, 50 iterationsTest FER: 0.37 -> 0.11Improved
Add retraining with Δ1=5 and Δ2=10 rather than no retraining with Δ1=5 (ablation)NMS decoder · WiMAX LDPC, block-wise parameter searchTest FER: 0.193 -> 0.112Improved
Increase block size from Δ1=1 to Δ1=10 with no retraining (ablation)NMS decoder · WiMAX LDPC, block-wise parameter searchTest FER: 0.376 -> 0.142Improved
Replace boosting with a single large network of the same model size (ablation)NMS decoder · WiMAX LDPC, error-floor regionFERHurt
Use spatial or temporal sharing instead of dynamic UCN/SCN weights (ablation)NMS decoder · WiMAX LDPC, error-floor regionFERHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy