paper-with-me

Papers

LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representations

2023-10-13 · Ahmed Khalil, Robert Piechocki, Raul Santos-Rodriguez

In this paper we introduce learnable lattice vector quantization and demonstrate its effectiveness for learning discrete representations. Our method, termed LL-VQ-VAE, replaces the vector quantization layer in VQ-VAE with lattice-based discretization. The learnable lattice imposes a structure over all discrete embeddings, acting as a deterrent against codebook collapse, leading to high codebook utilization. Compared to VQ-VAE, our method obtains lower reconstruction errors under the same training conditions, trains in a fraction of the time, and with a constant number of parameters (equal to the embedding dimension $D$), making it a very scalable approach. We demonstrate these results on the FFHQ-1024 dataset and include FashionMNIST and Celeb-A.

📄 PDF Abstract BibTeX arXiv:2310.09382

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

VQ-VAE VQ-VAE is a type of variational autoencoder that uses vector quantisation to obtain a discrete latent representation. It differs from…

Similar Papers 제목 키워드 기반

Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression

2025-10-23 · Xi Zhang, Xiaolin Wu, Jiamang Wang, Weisi Lin arxiv

Large Language Models (LLMs) have demonstrated remarkable capabilities but typically require extensive computational resources and memory for inference. Post-training quantization (PTQ) can effectively reduce these deman…

Lattice Representation Learning

2019-09-25 · Luis A Lastras

We introduce the notion of \emph{lattice representation learning}, in which the representation for some object of interest (e.g. a sentence or an image) is a lattice point in an Euclidean space. Our main contribution is …

DecoderQuantizationRepresentation LearningSentence

Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression

2024-11-25 · Xi Zhang, Xiaolin Wu

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter. Lattice vector q…

Computational EfficiencyImage CompressionQuantization

Multirate Neural Image Compression with Adaptive Lattice Vector Quantization

2025-01-01 · CVPR 2025 1 · Hao Xu, Xiaolin Wu, Xi Zhang

Recent research has explored integrating lattice vector quantization (LVQ) into learned image compression models. Due to its more efficient Voronoi covering of vector space than scalar quantization (SQ), LVQ achieves…

Domain AdaptationImage CompressionQuantization

Leech Lattice Vector Quantization for Efficient LLM Compression

2026-03-11 · Tycho F. A. van der Ouderaa, Mart van Baalen, Paul Whatmough, Markus Nagel arxiv

Scalar quantization of large language models (LLMs) is fundamentally limited by information-theoretic bounds. While vector quantization (VQ) overcomes these limits by encoding blocks of parameters jointly, practical impl…

Model Compression