English
Related papers

Related papers: On Stochastic Rounding with Few Random Bits

200 papers

Due to the limited number of bits in floating-point or fixed-point arithmetic, rounding is a necessary step in many computations. Although rounding methods can be tailored for different applications, round-off errors are generally…

Numerical Analysis · Mathematics 2020-06-02 Lu Xia , Martijn Anthonissen , Michiel Hochstenbach , Barry Koren

Stochastic rounding (SR) is a probabilistic method used to round numbers to floating-point and fixed-point representations. In length $n$ summation, the worst-case error of SR grows as $\sqrt{n}$ with high probability, unlike for standard…

Numerical Analysis · Mathematics 2026-03-09 El-Mehdi El Arar , Massimiliano Fasi , Silviu-Ioan Filip , Mantas Mikaitis

Classical probabilistic rounding error analysis is particularly well suited to stochastic rounding (SR), and it yields strong results when dealing with floating-point algorithms that rely heavily on summation. For many numerical linear…

Numerical Analysis · Mathematics 2025-02-26 El-Mehdi El Arar , Massimiliano Fasi , Silviu-Ioan Filip , Mantas Mikaitis

Stochastic rounding (SR) is a probabilistic rounding mode that mitigates errors in large-scale numerical computations, especially when prone to stagnation effects. Beyond numerical analysis, SR has shown significant benefits in practical…

Numerical Analysis · Mathematics 2026-03-26 El-Mehdi El Arar , Massimiliano Fasi , Silviu-Ioan Filip , Mantas Mikaitis

Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations. We introduce an improved stochastic rounding method, that is simple…

Machine Learning · Computer Science 2021-03-26 Lu Xia , Martijn Anthonissen , Michiel Hochstenbach , Barry Koren

Stochastic Rounding is a probabilistic rounding mode that is surprisingly effective in large-scale computations and low-precision arithmetic. Its random nature promotes error cancellation rather than error accumulation, resulting in slower…

Numerical Analysis · Mathematics 2024-10-15 Petros Drineas , Ilse C. F. Ipsen

Algorithms and a hardware accelerator for performing stochastic rounding (SR) are presented. The main goal is to augment the ARM M4F based multi-core processor SpiNNaker2 with a more flexible rounding functionality than is available in the…

Hardware Architecture · Computer Science 2020-07-01 Mantas Mikaitis

Stochastic rounding (SR) offers an alternative to the deterministic IEEE-754 floating-point rounding modes. In some applications such as PDEs, ODEs and neural networks, SR empirically improves the numerical behavior and convergence to…

Numerical Analysis · Mathematics 2023-06-06 El-Mehdi El Arar , Devan Sohier , Pablo de Oliveira Castro , Eric Petit

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade model accuracy. Stochastic Rounding (SR) has emerged as a…

Machine Learning · Computer Science 2025-11-04 Taowen Liu , Marta Andronic , Deniz Gündüz , George A. Constantinides

Recently, stochastic rounding (SR) has been implemented in specialized hardware but most current computing nodes do not yet support this rounding mode. Several works empirically illustrate the benefit of stochastic rounding in various…

Numerical Analysis · Mathematics 2022-07-11 El-Mehdi El Arar , Devan Sohier , Pablo de Oliveira Castro , Eric Petit

When implementing the gradient descent method in low precision, the employment of stochastic rounding schemes helps to prevent stagnation of convergence caused by the vanishing gradient effect. Unbiased stochastic rounding yields zero bias…

Machine Learning · Computer Science 2023-02-28 Lu Xia , Stefano Massei , Michiel E. Hochstenbach , Barry Koren

The stochastic simulation algorithm (SSA) is widely used to perform exact forward simulation of discrete stochastic processes in biology. However, the computational cost, driven by sequential event-by-event sampling across large ensembles,…

Quantitative Methods · Quantitative Biology 2026-05-04 Tom Kimpson , Mark B. Flegg , Jennifer A. Flegg

Training Deep Neural Networks (DNNs) can be computationally demanding, particularly when dealing with large models. Recent work has aimed to mitigate this computational challenge by introducing 8-bit floating-point (FP8) formats for…

Hardware Architecture · Computer Science 2024-09-27 Sami Ben Ali , Silviu-Ioan Filip , Olivier Sentieys

Finite-precision floating point arithmetic unavoidably introduces rounding errors which are traditionally bounded using a worst-case analysis. However, worst-case analysis might be overly conservative because worst-case errors can be…

Numerical Analysis · Mathematics 2019-12-11 Fredrik Dahlqvist , Rocco Salvia , George A Constantinides

Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of…

Machine Learning · Computer Science 2015-02-11 Suyog Gupta , Ankur Agrawal , Kailash Gopalakrishnan , Pritish Narayanan

Modern computer architectures support low-precision arithmetic, which present opportunities for the adoption of mixed-precision algorithms to achieve high computational throughput and reduce energy consumption. As a growing number of…

Computation · Statistics 2024-12-02 Sahil Bhola , Karthik Duraisamy

Although double-precision floating-point arithmetic currently dominates high-performance computing, there is increasing interest in smaller and simpler arithmetic types. The main reasons are potential improvements in energy efficiency and…

Data Structures and Algorithms · Computer Science 2020-01-23 Michael Hopkins , Mantas Mikaitis , Dave R. Lester , Steve Furber

We introduce new rounding methods to improve the accuracy of finite precision quantum arithmetic. These quantum rounding methods are applicable when multiple samples are being taken from a quantum program. We show how to use multiple…

Quantum Physics · Physics 2021-08-18 Rajiv Krishnakumar , William Zeng

Neural network algorithms simulated on standard computing platforms typically make use of high resolution weights, with floating-point notation. However, for dedicated hardware implementations of such algorithms, fixed-point synaptic…

Neural and Evolutionary Computing · Computer Science 2015-04-23 Lorenz K. Muller , Giacomo Indiveri

The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of…

Machine Learning · Computer Science 2018-04-17 Marc Ortiz , Adrián Cristal , Eduard Ayguadé , Marc Casas
‹ Prev 1 2 3 10 Next ›