paper-with-me

Papers

Variational Network Quantization

2018-01-01 · ICLR 2018 1 · Jan Achterhold, Jan Mathias Koehler, Anke Schmeink, Tim Genewein

In this paper, the preparation of a neural network for pruning and few-bit quantization is formulated as a variational inference problem. To this end, a quantizing prior that leads to a multi-modal, sparse posterior distribution over weights, is introduced and a differentiable Kullback-Leibler divergence approximation for this prior is derived. After training with Variational Network Quantization, weights can be replaced by deterministic quantization values with small to negligible loss of task accuracy (including pruning by setting weights to 0). The method does not require fine-tuning after quantization. Results are shown for ternary quantization on LeNet-5 (MNIST) and DenseNet (CIFAR-10).

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

QuantizationVariational Inference

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Dense Block A Dense Block is a module used in convolutional neural networks that connects *all layers* (with matching feature-map sizes) directly with each other. It was originally…

Similar Papers 제목 키워드 기반

SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization

2022-05-16 · Yuhta Takida, Takashi Shibuya, WeiHsiang Liao, Chieh-Hsin Lai 외

One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize …

Quantization

On the relation between trainability and dequantization of variational quantum learning models

2024-06-11 · Elies Gil-Fuster, Casper Gyurik, Adrián Pérez-Salinas, Vedran Dunjko

The quest for successful variational quantum machine learning (QML) relies on the design of suitable parametrized quantum circuits (PQCs), as analogues to neural networks in classical machine learning. Successful QML mod…

Quantum Machine LearningRelation

Soft then Hard: Rethinking the Quantization in Neural Image Compression

2021-04-12 · Zongyu Guo, Zhizheng Zhang, Runsen Feng, Zhibo Chen

Quantization is one of the core components in lossy image compression. For neural image compression, end-to-end optimization requires differentiable approximations of quantization, which can generally be grouped into thr…

Image CompressionQuantization

Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification

2025-12-11 · Hendrik Borras, Yong Wu, Bernhard Klein, Holger Fröning arxiv

Bayesian Neural Networks (BNNs) provide principled uncertainty quantification but suffer from substantial computational and memory overhead compared to deterministic networks. While quantization techniques have successfu…

Image Classification

Variational Bayesian Quantization

2020-02-18 · ICML 2020 1 · Yibo Yang, Robert Bamler, Stephan Mandt

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…

Image CompressionModel CompressionQuantizationWord Embeddings