Efficient Computation of Hessian Matrices in TensorFlow

05/14/2019
by   Geir K. Nilsen, et al.
0

The Hessian matrix has a number of important applications in a variety of different fields, such as optimzation, image processing and statistics. In this paper we focus on the practical aspects of efficiently computing Hessian matrices in the context of deep learning using the Python scripting language and the TensorFlow library.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/11/2021

Estimating accurate covariance matrices on fitted model parameters

The accurate computation of the covariance matrix of fitted model parame...
research
07/29/2020

A new framework for the computation of Hessians

We investigate the computation of Hessian matrices via Automatic Differe...
research
12/02/2019

On the Delta Method for Uncertainty Approximation in Deep Learning

The Delta method is a well known procedure used to quantify uncertainty ...
research
05/27/2021

TensorFlow RiemOpt: a library for optimization on Riemannian manifolds

The adoption of neural networks and deep learning in non-Euclidean domai...
research
09/16/2017

Feedforward and Recurrent Neural Networks Backward Propagation and Hessian in Matrix Form

In this paper we focus on the linear algebra theory behind feedforward (...
research
10/17/2020

A Systematic Approach to Computing the Manipulator Jacobian and Hessian using the Elementary Transform Sequence

The elementary transform sequence (ETS) provides a universal method of d...
research
11/28/2017

TensorFlow Distributions

The TensorFlow Distributions library implements a vision of probability ...

Please sign up or login with your details

Forgot password? Click here to reset