Picture for Michiel Hochstenbach

Michiel Hochstenbach

On the influence of roundoff errors on the convergence of the gradient descent method with low-precision floating-point computation

Add code
Feb 24, 2022
Figure 1 for On the influence of roundoff errors on the convergence of the gradient descent method with low-precision floating-point computation
Figure 2 for On the influence of roundoff errors on the convergence of the gradient descent method with low-precision floating-point computation
Figure 3 for On the influence of roundoff errors on the convergence of the gradient descent method with low-precision floating-point computation
Figure 4 for On the influence of roundoff errors on the convergence of the gradient descent method with low-precision floating-point computation
Viaarxiv icon

A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision

Add code
Mar 24, 2021
Figure 1 for A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision
Figure 2 for A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision
Figure 3 for A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision
Figure 4 for A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision
Viaarxiv icon

Improved stochastic rounding

Add code
May 31, 2020
Figure 1 for Improved stochastic rounding
Figure 2 for Improved stochastic rounding
Figure 3 for Improved stochastic rounding
Figure 4 for Improved stochastic rounding
Viaarxiv icon