mlsanityData to 14 Oct 2026

Quantization Design for Deep Learning-Based CSI Feedback

arXiv 2503.08125 ↗First posted 11 Mar 2025eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning-based autoencoders have been employed to compress and reconstruct channel state information (CSI) in frequency-division duplex systems. Practical implementations require judicious quantization of encoder outputs for digital transmission. In this paper, we propose a novel quantization module with bit allocation among encoder outputs and develop a method for joint training the module and the autoencoder. To enhance learning performance, we design a loss function that adaptively weights the quantization loss and the logarithm of reconstruction loss. Simulation results show the performance gain of the proposed method over existing baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 21 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

12 of 21 references.

References · 12

  1. 2023Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networkscited by 82
  2. 2022Overview of Deep Learning-based CSI Feedback in Massive MIMO Systemscited by 37
  3. 2019Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysiscited by 35
  4. 2019Multi-resolution CSI Feedback with deep learning in Massive MIMO Systemcited by 32
  5. 2020Distributed Deep Convolutional Compression for Massive MIMO CSI Feedbackcited by 22
  6. 2017Fast Exact k-Means, k-Medians and Bregman Divergence Clustering in 1Dcited by 15
  7. 2019An Efficient Deep Learning Framework for Low Rate Massive MIMO CSI Reportingcited by 12
  8. 2022Changeable Rate and Novel Quantization for CSI Feedback Based on Deep Learningcited by 9
  9. 2022Deep CSI Compression for Massive MIMO: A Self-information Model-driven Neural Networkcited by 9
  10. 2022Machine Learning-Based CSI Feedback With Variable Length in FDD Massive MIMOcited by 6
  11. 2022A Learnable Optimization and Regularization Approach to Massive MIMO CSI Feedbackcited by 2
  12. 2022CSI-PPPNet: A One-Sided One-for-All Deep Learning Framework for Massive MIMO CSI Feedbackcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Learning Representations for CSI Adaptive Quantization and Feedback
  2. 2024Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems
  3. 2025Information-Preserving CSI Feedback: Invertible Networks with Endogenous Quantization and Channel Error Mitigation
  4. 2022Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback
  5. 2024An Efficient Network with Novel Quantization Designed for Massive MIMO CSI Feedback
  6. 2025Deep Learning-Based CSI Feedback for Wi-Fi Systems With Temporal Correlation ↗
  7. 2024Deep Learning-based CSI Feedback in Wi-Fi Systems ↗
  8. 2026Precoding-Oriented CSI Feedback Design with Mutual Information Regularized VQ-VAE