English
Related papers

Related papers: BayesQ: Uncertainty-Guided Bayesian Quantization

200 papers

Post-training model quantization is a widely adopted technique for reducing the memory and computational costs of large language models (LLMs). However, most existing methods rely on uniform or heuristic bitwidth assignments, failing to…

Machine Learning · Computer Science 2025-06-09 Chao Zhang , Li Wang , Samson Lasaulce , Merouane Debbah

While neural networks have been remarkably successful in a wide array of applications, implementing them in resource-constrained hardware remains an area of intense research. By replacing the weights of a neural network with quantized…

Machine Learning · Computer Science 2023-01-18 Jinjie Zhang , Yixuan Zhou , Rayan Saab

Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining, but can degrade its downstream performance especially in low 2- to 3-bit settings. We…

Machine Learning · Computer Science 2025-07-18 Hanqi Xiao , Yi-Lin Sung , Elias Stengel-Eskin , Mohit Bansal

Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Jiawei Liu , Lin Niu , Zhihang Yuan , Dawei Yang , Xinggang Wang , Wenyu Liu

Uncertainty quantification plays an important role in achieving trustworthy and reliable learning-based computational imaging. Recent advances in generative modeling and Bayesian neural networks have enabled the development of…

Image and Video Processing · Electrical Eng. & Systems 2025-10-07 Canberk Ekmekci , Mujdat Cetin

Large Language Models (LLMs) are widely used across many domains, but their scale makes deployment challenging. Post-Training Quantization (PTQ) reduces memory footprint without retraining by leveraging a small calibration set. Recent…

Machine Learning · Computer Science 2026-04-16 Jaemin Kim , Sungkyun Kim , Junyeol Lee , Jiwon Seo

The standard asymmetric Laplace framework for Bayesian quantile regression (BQR) suffers from a fundamental decision-theoretic misalignment, yielding biased finite-sample estimates, and precludes gradient-based computation due to…

Methodology · Statistics 2026-01-14 Bingqi Liu , Kangqiang Li , Tianxiao Pang

We provide a general solution to a fundamental open problem in Bayesian inference, namely poor uncertainty quantification, from a frequency standpoint, of Bayesian methods in misspecified models. While existing solutions are based on…

Methodology · Statistics 2023-02-14 David T. Frazier , Robert Kohn , Christopher Drovandi , David Gunawan

Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the…

Machine Learning · Computer Science 2021-02-23 Huanrui Yang , Lin Duan , Yiran Chen , Hai Li

Epistemic uncertainty quantification (UQ) identifies where models lack knowledge. Traditional UQ methods, often based on Bayesian neural networks, are not suitable for pre-trained non-Bayesian models. Our study addresses quantifying…

Machine Learning · Computer Science 2024-04-17 Hanjing Wang , Qiang Ji

Efficiently serving neural network models with low latency is becoming more challenging due to increasing model complexity and parameter count. Model quantization offers a solution which simultaneously reduces memory footprint and compute…

While neural networks have demonstrated impressive performance across various tasks, accurately quantifying uncertainty in their predictions is essential to ensure their trustworthiness and enable widespread adoption in critical systems.…

Machine Learning · Statistics 2025-11-11 Joseph Wilson , Chris van der Heide , Liam Hodgkinson , Fred Roosta

We study weight-only post-training quantization (PTQ), which quantizes the weights of a large language model (LLM) without retraining, using little or no calibration data. Weight-only PTQ is crucial for reducing the memory footprint and…

Machine Learning · Computer Science 2025-10-23 Deokjae Lee , Hyun Oh Song

Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Ruihao Gong , Xianglong Liu , Shenghu Jiang , Tianxiang Li , Peng Hu , Jiazhen Lin , Fengwei Yu , Junjie Yan

Bayesian inference promises a framework for principled uncertainty quantification of neural network predictions. Barriers to adoption include the difficulty of fully characterizing posterior distributions on network parameters and the…

Machine Learning · Statistics 2025-01-22 Katharine Fisher , Youssef Marzouk

Quantization is a key method for deploying deep neural networks on edge devices with limited memory and computation resources. Recent improvements in Post-Training Quantization (PTQ) methods were achieved by an additional local optimization…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Ofir Gordon , Elad Cohen , Hai Victor Habi , Arnon Netzer

Estimated uncertainty by approximate posteriors in Bayesian neural networks are prone to miscalibration, which leads to overconfident predictions in critical tasks that have a clear asymmetric cost or significant losses. Here, we extend the…

Machine Learning · Computer Science 2022-06-17 Biraja Ghoshal , Allan Tucker

Currently available quantum computers suffer from constraints including hardware noise and a limited number of qubits. As such, variational quantum algorithms that utilise a classical optimiser in order to train a parameterised quantum…

Quantum Physics · Physics 2023-04-18 Samuel Duffield , Marcello Benedetti , Matthias Rosenkranz

Inverse Uncertainty Quantification (UQ) is a process to quantify the uncertainties in random input parameters while achieving consistency between code simulations and physical observations. In this paper, we performed inverse UQ using an…

Applications · Statistics 2018-06-22 Xu Wu , Tomasz Kozlowski , Hadi Meidani , Koroush Shirvan

Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight pruning or low-bit quantization individually, often resulting in suboptimal compression rates to…

Machine Learning · Computer Science 2025-10-13 Ziyi Wang , Nan Jiang , Guang Lin , Qifan Song
‹ Prev 1 2 3 10 Next ›