Relativized Separation of Reversible and Irreversible Space-Time Complexity Classes

08/28/2017 ∙ by Michael P. Frank, et al. ∙ 0

Reversible computing can reduce the energy dissipation of computation, which can improve cost-efficiency in some contexts. But the practical applicability of this method depends sensitively on the space and time overhead required by reversible algorithms. Time and space complexity classes for reversible machines match conventional ones, but we conjecture that the joint space-time complexity classes are different, and that a particular reduction by Bennett minimizes the space-time product complexity of general reversible computations. We provide an oracle-relativized proof of the separation, and of a lower bound on space for linear-time reversible simulations. A non-oracle proof applies when a read-only input is omitted from the space accounting. Both constructions model one-way function iteration, conjectured to be a problem for which Bennett's algorithm is optimal.



There are no comments yet.


page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.