English
Related papers

Related papers: 8-bit Optimizers via Block-wise Quantization

200 papers

This paper introduces the notion of soft bits to address the rate-distortion optimization for learning-based image compression. Recent methods for such compression train an autoencoder end-to-end with an objective to strike a balance…

Image and Video Processing · Electrical Eng. & Systems 2019-05-02 David Alexandre , Chih-Peng Chang , Wen-Hsiao Peng , Hsueh-Ming Hang

Quantum Variational Circuits (QVCs) are often claimed as one of the most potent uses of both near term and long term quantum hardware. The standard approaches to optimizing these circuits rely on a classical system to compute the new…

Quantum Physics · Physics 2022-02-11 Owen Lockwood

Retrieval-Augmented Generation enhances language models by retrieving relevant information from external knowledge bases, relying on high-dimensional vector embeddings typically stored in float32 precision. However, storing these embeddings…

Gradient descent method, as one of the major methods in numerical optimization, is the key ingredient in many machine learning algorithms. As one of the most fundamental way to solve the optimization problems, it promises the function value…

Quantum Physics · Physics 2021-02-01 Keren Li , Shijie Wei , Feihao Zhang , Pan Gao , Zengrong Zhou , Tao Xin , Xiaoting Wang , Guilu Long

We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit…

Machine Learning · Computer Science 2019-11-26 Markus Nagel , Mart van Baalen , Tijmen Blankevoort , Max Welling

Quantization is a technique used in deep neural networks (DNNs) to increase execution performance and hardware efficiency. Uniform post-training quantization (PTQ) methods are common, since they can be implemented efficiently in hardware…

Machine Learning · Computer Science 2021-10-29 Gil Shomron , Freddy Gabbay , Samer Kurzum , Uri Weiser

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradient descent. In this…

Machine Learning · Computer Science 2019-05-27 Shuai Zheng , James T. Kwok

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the…

Machine Learning · Computer Science 2026-02-19 Tianyi Chen , Sihan Chen , Xiaoyi Qu , Dan Zhao , Ruomei Yan , Jongwoo Ko , Luming Liang , Pashmina Cameron

Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent…

Machine Learning · Computer Science 2018-02-02 Chen Xu , Jianqiang Yao , Zhouchen Lin , Wenwu Ou , Yuanbin Cao , Zhirong Wang , Hongbin Zha

In this work we show that randomized (block) coordinate descent methods can be accelerated by parallelization when applied to the problem of minimizing the sum of a partially separable smooth convex function and a simple separable convex…

Optimization and Control · Mathematics 2013-11-27 Peter Richtárik , Martin Takáč

Symbolic regression that aims to detect underlying data-driven models has become increasingly important for industrial data analysis. For most existing algorithms such as genetic programming (GP), the convergence speed might be too slow for…

Neural and Evolutionary Computing · Computer Science 2017-10-31 Chen Chen , Changtong Luo , Zonglin Jiang

Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and…

Machine Learning · Computer Science 2026-04-10 Binxing Xu , Hao Gu , Lujun Li , Hao Wang , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Xintong Yang , Chao Li , Sirui Han , Yike Guo

Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Hsin-Pai Cheng , Yuanjun Huang , Xuyang Guo , Yifei Huang , Feng Yan , Hai Li , Yiran Chen

Modern 3D image recovery problems require powerful optimization frameworks to handle high dimensionality while providing reliable numerical solutions in a reasonable time. In this perspective, asynchronous parallel optimization algorithms…

Optimization and Control · Mathematics 2020-06-26 Mathieu Chalvidal , Emilie Chouzenoux

Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with quantized gradients can further bring more considerable acceleration, since the backward…

Machine Learning · Computer Science 2020-01-01 Feng Zhu , Ruihao Gong , Fengwei Yu , Xianglong Liu , Yanfei Wang , Zhelong Li , Xiuqi Yang , Junjie Yan

We consider whether conditions exist under which block-coordinate descent is asymptotically efficient in evolutionary multi-objective optimization, addressing an open problem. Block-coordinate descent, where an optimization problem is…

Neural and Evolutionary Computing · Computer Science 2024-07-17 Benjamin Doerr , Joshua Knowles , Aneta Neumann , Frank Neumann

There has been many papers in academic literature on quantizing weight tensors in deep learning models to reduce inference latency and memory footprint. TVM also has the ability to quantize weights and support low-bit computations. Although…

Machine Learning · Computer Science 2023-08-23 Mingfei Guo

We propose a novel 2-stage sub 8-bit quantization aware training algorithm for all components of a 250K parameter feedforward, streaming, state-free keyword spotting model. For the 1st-stage, we adapt a recently proposed quantization…

Optimizer states occupy massive GPU memory in large-scale model training. However, gradients in different network blocks exhibit distinct behaviors, such as varying directional stability and scale anisotropy, implying that expensive…

Artificial Intelligence · Computer Science 2026-05-07 Kang Liu , Wei Peng , Jianchen Hu

Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the normalization-induced scale invariance among the weights…

Machine Learning · Computer Science 2021-01-19 Byeongho Heo , Sanghyuk Chun , Seong Joon Oh , Dongyoon Han , Sangdoo Yun , Gyuwan Kim , Youngjung Uh , Jung-Woo Ha