paper-with-me

Papers

Learning Linear Block Codes with Gradient Quantization

2025-03-20 · Louis-Adrien Dufrène, Quentin Lampin, Guillaume Larue

This study investigates the problem of learning linear block codes optimized for Belief-Propagation decoders significantly improving performance compared to the state-of-the-art. Our previous research is extended with an enhanced system design that facilitates a more effective learning process for the parity check matrix. We simplify the input dataset, restrict the number of parameters to learn and improve the gradient back-propagation within the model. We also introduce novel optimizers specifically designed for discrete-valued weights. Based on conventional gradient computation, these optimizers provide discrete weights updates, enabling finer control and improving explainability of the learning process. Through these changes, we consistently achieve improved code performance, provided appropriately chosen hyper-parameters. To rigorously evaluate the performance of learned codes in the context of short to medium block lengths, we propose a comprehensive code performance assessment framework. This framework enables a fair comparison between our learning methodology and random search approaches, ensuring statistical significance in our results. The proposed model pave the way for a new approach to the efficient learning of linear block codes tailored to specific decoder structures.

📄 PDF Abstract BibTeX arXiv:2503.16169

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderQuantization

Methods 이 논문이 사용한 방법론

Random Search Random Search replaces the exhaustive enumeration of all combinations by selecting them randomly. This can be simply applied to the discrete setting described above, but also…

Similar Papers 제목 키워드 기반

Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart

2024-12-20 · Chengting Yu, Shu Yang, Fengzhao Zhang, Hanzhi Ma 외

Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignme…

Quantization

8-bit Optimizers via Block-wise Quantization

2021-10-06 · ICLR 2022 4 · Tim Dettmers, Mike Lewis, Sam Shleifer, Luke Zettlemoyer

Stateful optimizers maintain gradient statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past gradient values. This state can be used to accelerate optimization compar…

Language ModelingLanguage ModellingMachine TranslationQuantization

Learning Linear Block Error Correction Codes

2024-05-07 · Yoni Choukroun, Lior Wolf

Error correction codes are a crucial part of the physical communication layer, ensuring the reliable transfer of data over noisy channels. The design of optimal linear block codes capable of being efficiently decoded is …

Decoder

Push for Quantization: Deep Fisher Hashing

2019-08-31 · Yunqiang Li, Wenjie Pei, Yufei zha, Jan van Gemert

Current massive datasets demand light-weight access for analysis. Discrete hashing methods are thus beneficial because they map high-dimensional data to compact binary codes that are efficient to store and process, while…

QuantizationSemantic SimilaritySemantic Textual Similarity

Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval

2019-06-16 · Lianli Gao, Xiaosu Zhu, Jingkuan Song, Zhou Zhao 외

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector s…

Image RetrievalQuantizationRetrieval