Memory-minimal quantum generation of stochastic processes: spectral invariants of quantum hidden Markov models
Magdalini Zonnios, Alec Boyd, Felix C. Binder

TL;DR
This paper introduces spectral invariants for quantum hidden Markov models that determine the minimal memory required to generate a process, revealing quantum advantages over classical models and providing bounds on quantum complexity.
Contribution
It identifies spectral invariants that can be computed from any model generating a process, establishing bounds on quantum and classical memory requirements and demonstrating quantum advantages.
Findings
Spectral invariants determine minimal quantum memory for process generation.
Quantum models can violate classical memory bounds, showing quantum advantage.
Memory bounds increase quadratically when restricted to classical operations.
Abstract
Stochastic processes abound in nature and accurately modeling them is essential across the quantitative sciences. They can be described by hidden Markov models (HMMs) or by their quantum extensions (QHMMs). These models explain and give rise to process outputs in terms of an observed system interacting with an unobserved memory. Although there are infinitely many models that can generate a given process, they can vary greatly in their memory requirements. It is therefore of great fundamental and practical importance to identify memory-minimal models. This task is complicated due to both the number of generating models, and the lack of invariant features that determine elements of the set. In general, it is forbiddingly difficult to ascertain that a given model is minimal. Addressing this challenge, we here identify spectral invariants of a process that can be calculated from any model…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications · Neural Networks and Reservoir Computing
