AlphaZip: Neural Network-Enhanced Lossless Text Compression
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929510891388928 |
|---|---|
| author | Narashiman, Swathi Shree Chandrachoodan, Nitin |
| author_facet | Narashiman, Swathi Shree Chandrachoodan, Nitin |
| contents | Data compression continues to evolve, with traditional information theory methods being widely used for compressing text, images, and videos. Recently, there has been growing interest in leveraging Generative AI for predictive compression techniques. This paper introduces a lossless text compression approach using a Large Language Model (LLM). The method involves two key steps: first, prediction using a dense neural network architecture, such as a transformer block; second, compressing the predicted ranks with standard compression algorithms like Adaptive Huffman, LZ77, or Gzip. Extensive analysis and benchmarking against conventional information-theoretic baselines demonstrate that neural compression offers improved performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15046 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AlphaZip: Neural Network-Enhanced Lossless Text Compression Narashiman, Swathi Shree Chandrachoodan, Nitin Information Theory Artificial Intelligence Machine Learning Data compression continues to evolve, with traditional information theory methods being widely used for compressing text, images, and videos. Recently, there has been growing interest in leveraging Generative AI for predictive compression techniques. This paper introduces a lossless text compression approach using a Large Language Model (LLM). The method involves two key steps: first, prediction using a dense neural network architecture, such as a transformer block; second, compressing the predicted ranks with standard compression algorithms like Adaptive Huffman, LZ77, or Gzip. Extensive analysis and benchmarking against conventional information-theoretic baselines demonstrate that neural compression offers improved performance. |
| title | AlphaZip: Neural Network-Enhanced Lossless Text Compression |
| topic | Information Theory Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.15046 |