English
Related papers

Related papers: BayesQ: Uncertainty-Guided Bayesian Quantization

200 papers

Bayesian quadrature (BQ) is a model-based numerical integration method that is able to increase sample efficiency by encoding and leveraging known structure of the integration task at hand. In this paper, we explore priors that encode…

Machine Learning · Statistics 2021-12-06 Masha Naslidnyk , Javier Gonzalez , Maren Mahsereci

We develop a weighted Bayesian Bootstrap (WBB) for machine learning and statistics. WBB provides uncertainty quantification by sampling from a high dimensional posterior distribution. WBB is computationally fast and scalable using only…

Methodology · Statistics 2021-04-06 Michael Newton , Nicholas G. Polson , Jianeng Xu

Being able to reliably assess not only the \emph{accuracy} but also the \emph{uncertainty} of models' predictions is an important endeavour in modern machine learning. Even if the model generating the data and labels is known, computing the…

Machine Learning · Computer Science 2023-09-12 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get…

Machine Learning · Computer Science 2023-02-13 Nilesh Prasad Pandey , Markus Nagel , Mart van Baalen , Yin Huang , Chirag Patel , Tijmen Blankevoort

We propose a novel, succinct, and effective approach for distribution prediction to quantify uncertainty in machine learning. It incorporates adaptively flexible distribution prediction of $\mathbb{P}(\mathbf{y}|\mathbf{X}=x)$ in regression…

Machine Learning · Computer Science 2023-06-21 Xing Yan , Yonghua Su , Wenxuan Ma

The Bayesian Conjugate Gradient method (BayesCG) is a probabilistic generalization of the Conjugate Gradient method (CG) for solving linear systems with real symmetric positive definite coefficient matrices. Our CG-based implementation of…

Numerical Analysis · Mathematics 2022-10-04 Tim W. Reid , Ilse C. F. Ipsen , Jon Cockayne , Chris J. Oates

Quantization has become a crucial step for the efficient deployment of deep neural networks, where floating point operations are converted to simpler fixed point operations. In its most naive form, it simply consists in a combination of…

Machine Learning · Computer Science 2023-08-16 Edouard Yvinec , Arnaud Dapogny , Kevin Bailly

Bayesian methods are actively used for parameter identification and uncertainty quantification when solving nonlinear inverse problems with random noise. However, there are only few theoretical results justifying the Bayesian approach.…

Statistics Theory · Mathematics 2020-02-04 Vladimir Spokoiny

Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors. We argue this cost is often unnecessary, particularly when weight matrices exhibit fast singular value…

Machine Learning · Statistics 2026-05-05 Mame Diarra Toure , David A. Stephens

Bayesian learning of model parameters in neural networks is important in scenarios where estimates with well-calibrated uncertainty are important. In this paper, we propose Bayesian quantized networks (BQNs), quantized neural networks…

Machine Learning · Computer Science 2019-12-09 Jiahao Su , Milan Cvitkovic , Furong Huang

Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. Several existing sub 2-bit post-training quantization (PTQ) methods utilize a mix-precision scheme by leveraging an…

Machine Learning · Computer Science 2025-08-07 Jiaqi Zhao , Miao Zhang , Ming Wang , Yuzhang Shang , Kaihao Zhang , Weili Guan , Yaowei Wang , Min Zhang

Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks. In heteroskedastic regression, where the uncertainty of the…

Machine Learning · Computer Science 2026-03-03 Mikkel Jordahn , Jonas Vestergaard Jensen , James Harrison , Michael Riis Andersen , Mikkel N. Schmidt

This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance. Previous PTQ methods usually reduce compression error via performing…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Chen Lin , Zheyang Li , Bo Peng , Haoji Hu , Wenming Tan , Ye Ren , Shiliang Pu

Bayesian inference is a widely used technique for real-time characterization of quantum systems. It excels in experimental characterization in the low data regime, and when the measurements have degrees of freedom. A decisive factor for its…

Quantum Physics · Physics 2025-07-10 Alexandra Ramôa , Raffaele Santagati , Nathan Wiebe

Inverse problems aim to determine model parameters of a mathematical problem from given observational data. Neural networks can provide an efficient tool to solve these problems. In the context of Bayesian inverse problems, Uncertainty…

Numerical Analysis · Mathematics 2025-09-16 Andrea Tonini , Tan Bui-Thanh , Francesco Regazzoni , Luca Dede' , Alfio Quarteroni

We introduce Delta-Aware Quantization (DAQ), a data-free post-training quantization framework that preserves the knowledge acquired during post-training. Standard quantization objectives minimize reconstruction error but are agnostic to the…

Machine Learning · Computer Science 2026-03-25 Xiaoming Yu , Shize Tang , Guanghua Yu , Linchuan Xie , Song Liu , Jianchen Zhu , Feng Li

Convolutional neural networks require significant memory bandwidth and storage for intermediate computations, apart from substantial computing resources. Neural network quantization has significant benefits in reducing the amount of…

Computer Vision and Pattern Recognition · Computer Science 2019-05-30 Ron Banner , Yury Nahshan , Elad Hoffer , Daniel Soudry

Recent advances in reconstruction methods for inverse problems leverage powerful data-driven models, e.g., deep neural networks. These techniques have demonstrated state-of-the-art performances for several imaging tasks, but they often do…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Riccardo Barbano , Chen Zhang , Simon Arridge , Bangti Jin

Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau,…

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

Machine Learning · Statistics 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz