mlsanityData to 7 Oct 2026

CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family

arXiv 2210.00313 ↗First posted 1 Oct 2022cs.IT cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Polar codes are widely used state-of-the-art codes for reliable communication that have recently been included in the 5th generation wireless standards (5G). However, there remains room for the design of polar decoders that are both efficient and reliable in the short blocklength regime. Motivated by recent successes of data-driven channel decoders, we introduce a novel CurRIculum based Sequential neural decoder for Polar codes (CRISP). We design a principled curriculum, guided by information-theoretic insights, to train CRISP and show that it outperforms the successive-cancellation (SC) decoder and attains near-optimal reliability performance on the Polar(32,16) and Polar(64,22) codes. The choice of the proposed curriculum is critical in achieving the accuracy gains of CRISP, as we show by comparing against other curricula. More notably, CRISP can be readily extended to Polarization-Adjusted-Convolutional (PAC) codes, where existing SC decoders are significantly less reliable. To the best of our knowledge, CRISP constructs the first data-driven decoder for PAC codes and attains near-optimal performance on the PAC(32,16) code.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 51 of its 101 references that are in the map. First posted on arXiv 1 Oct 2022.

Builds on

51 of 101 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  10. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  11. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  12. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
38 more
  1. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  2. 2017An Introduction to Deep Learning for the Physical Layercited by 227
  3. 2016Professor Forcing: A New Algorithm for Training Recurrent Networkscited by 214
  4. 2019Competence-based Curriculum Learning for Neural Machine Translationcited by 201
  5. 2019Structured Pruning of Large Language Modelscited by 201
  6. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 148
  7. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  8. 2014Learning to Executecited by 105
  9. 2020When Do Curricula Work?cited by 105
  10. 2015Neural Programmer-Interpreterscited by 96
  11. 2019Dynamic Curriculum Learning for Imbalanced Data Classificationcited by 93
  12. 2014Curriculum Learning of Multiple Taskscited by 65
  13. 2016Learning to Decode Linear Codes Using Deep Learningcited by 60
  14. 2017Curriculum Dropoutcited by 50
  15. 2022Error Correction Code Transformercited by 47
  16. 2018A Fully Progressive Approach to Single-Image Super-Resolutioncited by 46
  17. 2016Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networkscited by 44
  18. 2018Communication Algorithms via Deep Learningcited by 42
  19. 2019Hyper-Graph-Network Decoders for Block Codescited by 42
  20. 2019Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channelscited by 42
  21. 2018Deepcode: Feedback Codes via Deep Learningcited by 41
  22. 2018Deep Learning for Decoding of Linear Codes - A Syndrome-Based Approachcited by 34
  23. 2017Neural Offset Min-Sum Decodingcited by 24
  24. 2022Denoising Diffusion Error Correction Codescited by 23
  25. 2017An Iterative BP-CNN Architecture for Channel Decodingcited by 18
  26. 2018CASED: Curriculum Adaptive Sampling for Extreme Data Imbalancecited by 16
  27. 2021KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learningcited by 16
  28. 2021ProductAE: Towards Training Larger Channel Codes based on Neural Product Codescited by 14
  29. 2016Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attentioncited by 13
  30. 2021Cyclically Equivariant Neural Decoders for Cyclic Codescited by 12
  31. 2020Pruning Neural Belief Propagation Decoderscited by 10
  32. 2019DeepTurbo: Deep Turbo Decodercited by 9
  33. 2017Performance Evaluation of Channel Decoding With Deep Neural Networkscited by 7
  34. 2020Model-Driven DNN Decoder for Turbo Codes: Design, Simulation and Experimental Resultscited by 3
  35. 2021Turbo Autoencoder with a Trainable Interleavercited by 3
  36. 2022TinyTurbo: Efficient Turbo Decoders on Edgecited by 3
  37. 2018Polar Decoding on Sparse Graphs with Deep Learningcited by 2
  38. 2019Learning to Denoise and Decode: A Novel Residual Neural Network Decoder for Polar Codescited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024LightCode: Light Analytical and Neural Codes for Channels with Feedbackcited by 4
  2. 2024Nested Construction of Polar Codes via Transformerscited by 2
  3. 2024DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learningcited by 1
  4. 2025Transformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errorscited by 1
  5. 2026In-Context Source and Channel Codingcited by 1