Effective and efficient forecasting relies on identification of the relevant information contained in past observations -- the predictive features -- and isolating it from the rest. When the future of a process bears a strong dependence on its behaviour far into the past, there are many such features to store, necessitating complex models with extensive memories. Here, we highlight a family of stochastic processes whose minimal classical models must devote unboundedly many bits to tracking the past. For this family, we identify quantum models of equal accuracy that can store all relevant information within a single two-dimensional quantum system (qubit). This represents the ultimate limit of quantum compression and highlights an immense practical advantage of quantum technologies for the forecasting and simulation of complex systems.
[1]
William.
IEEE TRANSACTIONS ON INFORMATION THEORY VOL XX NO Y MONTH Signal Propagation and Noisy Circuits
,
2019
.
[2]
Marco Tomamichel,et al.
Quantum Information Processing with Finite Resources - Mathematical Foundations
,
2015,
ArXiv.
[3]
M. Pollack.
Journal of Artificial Intelligence Research: Preface
,
2001
.
[4]
J. Herskowitz,et al.
Proceedings of the National Academy of Sciences, USA
,
1996,
Current Biology.
[5]
W. Marsden.
I and J
,
2012
.
[6]
L. Tippett,et al.
Applied Statistics. A Journal of the Royal Statistical Society
,
1952
.