Variational Bayesian Quantization
- URL: http://arxiv.org/abs/2002.08158v2
- Date: Mon, 7 Sep 2020 22:25:12 GMT
- Title: Variational Bayesian Quantization
- Authors: Yibo Yang, Robert Bamler and Stephan Mandt
- Abstract summary: We propose a novel algorithm for quantizing continuous latent representations in trained models.
Unlike current end-to-end neural compression methods that cater the model to a fixed quantization scheme, our algorithm separates model design and training from quantization.
Our algorithm can be seen as a novel extension of arithmetic coding to the continuous domain.
- Score: 31.999462074510305
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a novel algorithm for quantizing continuous latent representations
in trained models. Our approach applies to deep probabilistic models, such as
variational autoencoders (VAEs), and enables both data and model compression.
Unlike current end-to-end neural compression methods that cater the model to a
fixed quantization scheme, our algorithm separates model design and training
from quantization. Consequently, our algorithm enables "plug-and-play"
compression with variable rate-distortion trade-off, using a single trained
model. Our algorithm can be seen as a novel extension of arithmetic coding to
the continuous domain, and uses adaptive quantization accuracy based on
estimates of posterior uncertainty. Our experimental results demonstrate the
importance of taking into account posterior uncertainties, and show that image
compression with the proposed algorithm outperforms JPEG over a wide range of
bit rates using only a single standard VAE. Further experiments on Bayesian
neural word embeddings demonstrate the versatility of the proposed method.
Related papers
- Variational Bayes image restoration with compressive autoencoders [4.879530644978008]
Regularization of inverse problems is of paramount importance in computational imaging.
In this work, we first propose to use compressive autoencoders instead of state-of-the-art generative models.
As a second contribution, we introduce the Variational Bayes Latent Estimation (VBLE) algorithm.
arXiv Detail & Related papers (2023-11-29T15:49:31Z) - Quantization Aware Factorization for Deep Neural Network Compression [20.04951101799232]
decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks.
A conventional post-training quantization approach applied to networks with weights yields a drop in accuracy.
This motivated us to develop an algorithm that finds decomposed approximation directly with quantized factors.
arXiv Detail & Related papers (2023-08-08T21:38:02Z) - Towards Accurate Post-training Quantization for Diffusion Models [73.19871905102545]
We propose an accurate data-free post-training quantization framework of diffusion models (ADP-DM) for efficient image generation.
Our method outperforms the state-of-the-art post-training quantization of diffusion model by a sizable margin with similar computational cost.
arXiv Detail & Related papers (2023-05-30T04:00:35Z) - Regularized Vector Quantization for Tokenized Image Synthesis [126.96880843754066]
Quantizing images into discrete representations has been a fundamental problem in unified generative modeling.
deterministic quantization suffers from severe codebook collapse and misalignment with inference stage while quantization suffers from low codebook utilization and reconstruction objective.
This paper presents a regularized vector quantization framework that allows to mitigate perturbed above issues effectively by applying regularization from two perspectives.
arXiv Detail & Related papers (2023-03-11T15:20:54Z) - Modality-Agnostic Variational Compression of Implicit Neural
Representations [96.35492043867104]
We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR)
Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism.
After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression.
arXiv Detail & Related papers (2023-01-23T15:22:42Z) - Deblurring via Stochastic Refinement [85.42730934561101]
We present an alternative framework for blind deblurring based on conditional diffusion models.
Our method is competitive in terms of distortion metrics such as PSNR.
arXiv Detail & Related papers (2021-12-05T04:36:09Z) - Conditional Variational Autoencoder for Learned Image Reconstruction [5.487951901731039]
We develop a novel framework that approximates the posterior distribution of the unknown image at each query observation.
It handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned reconstructive properties are transferable between different datasets.
arXiv Detail & Related papers (2021-10-22T10:02:48Z) - Sigma-Delta and Distributed Noise-Shaping Quantization Methods for
Random Fourier Features [73.25551965751603]
We prove that our quantized RFFs allow a high accuracy approximation of the underlying kernels.
We show that the quantized RFFs can be further compressed, yielding an excellent trade-off between memory use and accuracy.
We empirically show by testing the performance of our methods on several machine learning tasks that our method compares favorably to other state of the art quantization methods in this context.
arXiv Detail & Related papers (2021-06-04T17:24:47Z) - Sampling-free Variational Inference for Neural Networks with
Multiplicative Activation Noise [51.080620762639434]
We propose a more efficient parameterization of the posterior approximation for sampling-free variational inference.
Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks.
arXiv Detail & Related papers (2021-03-15T16:16:18Z) - FracBits: Mixed Precision Quantization via Fractional Bit-Widths [29.72454879490227]
Mixed precision quantization is favorable with customized hardwares supporting arithmetic operations at multiple bit-widths.
We propose a novel learning-based algorithm to derive mixed precision models end-to-end under target computation constraints.
arXiv Detail & Related papers (2020-07-04T06:09:09Z) - Compressive MRI quantification using convex spatiotemporal priors and
deep auto-encoders [2.5060548079588516]
We propose a dictionary-free pipeline for multi-parametric image computing.
Our approach has two stages based on compressed sensing reconstruction and learned quantitative inference.
arXiv Detail & Related papers (2020-01-23T17:15:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.