An Exact Bitwise Reversible Integrator

07/15/2022
by   Jos Stam, et al.
0

At a fundamental level most physical equations are time reversible. In this paper we propose an integrator that preserves this property at the discrete computational level. Our simulations can be run forward and backwards and trace the same path exactly bitwise. We achieve this by implementing theoretically reversible integrators using a mix of fixed and floating point arithmetic. Our main application is in efficiently implementing the reverse step in the adjoint method used in optimization. Our integrator has applications in differential simulations and machine learning (backpropagation).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/10/2020

Differentiate Everything with a Reversible Domain-Specific Language

Traditional machine instruction level reverse mode automatic differentia...
research
08/16/2023

Towards Zero Memory Footprint Spiking Neural Network Training

Biologically-inspired Spiking Neural Networks (SNNs), processing informa...
research
04/19/2022

Globally time-reversible fluid simulations with smoothed particle hydrodynamics

This paper describes an energy-preserving and globally time-reversible c...
research
05/12/2021

Reversify any sequential algorithm

To reversify an arbitrary sequential algorithm A, we gently instrument A...
research
12/09/2019

Implementing the Exponential Mechanism with Base-2 Differential Privacy

Despite excellent theoretical support, Differential Privacy (DP) can sti...
research
10/25/2019

CrevNet: Conditionally Reversible Video Prediction

Applying resolution-preserving blocks is a common practice to maximize i...
research
01/26/2000

Numerical Replication of Computer Simulations: Some Pitfalls and How To Avoid Them

A computer simulation, such as a genetic algorithm, that uses IEEE stand...

Please sign up or login with your details

Forgot password? Click here to reset