paper-with-me

Papers

DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick

2025-09-30 · Mohammad Hassan Vali, Tom Bäckström, Arno Solin arxiv

Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping the forward pass hard while letting gradients flow. We also present a space-filling variant (SF-DiVeQ) that assigns input to a curve constructed by the lines connecting codewords, resulting in less quantization error and full codebook usage. Both methods train end-to-end without requiring auxiliary losses or temperature schedules. In VQ-VAE image compression, VQGAN image generation, and DAC speech coding tasks across various data sets, our proposed methods improve reconstruction and sample quality over alternative quantization approaches.

📄 PDF Abstract BibTeX arXiv:2509.26469

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionImage Generation

Similar Papers 제목 키워드 기반

GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training

2018-11-08 · NeurIPS 2018 12 · Mingchao Yu, Zhifeng Lin, Krishna Narra, Songze Li 외

Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation. To alleviate this problem, several scalar quanti…

Dimensionality ReductionQuantization

Reparameterization Gradient for Non-differentiable Models

2018-06-01 · NeurIPS 2018 12 · Wonyeol Lee, Hangyeol Yu, Hongseok Yang

We present a new algorithm for stochastic variational inference that targets at models with non-differentiable densities. One of the key challenges in stochastic variational inference is to come up with a low-variance es…

Variational Inference

Restructuring Vector Quantization with the Rotation Trick

2024-10-08 · Christopher Fifty, Ronald G. Junkins, Dennis Duan, Aniketh Iger 외

Vector Quantized Variational AutoEncoders (VQ-VAEs) are designed to compress a continuous input to a discrete latent space and reconstruct it with minimal distortion. They operate by maintaining a set of vectors -- often…

Quantization

Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms

2016-10-18 · Christian A. Naesseth, Francisco J. R. Ruiz, Scott W. Linderman, David M. Blei

Variational inference using the reparameterization trick has enabled large-scale approximate Bayesian inference in complex probabilistic models, leveraging stochastic optimization to sidestep intractable expectations. Th…

Bayesian InferenceStochastic OptimizationVariational Inference

End-to-End Training for Back-Translation with Categorical Reparameterization Trick

2022-02-17 · DongNyeong Heo, Heeyoul Choi

Back-translation (BT) is an effective semi-supervised learning framework in neural machine translation (NMT). A pre-trained NMT model translates monolingual sentences and makes synthetic bilingual sentence pairs for the …

Machine TranslationNMTSentenceTranslation