Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes

Abstract

Many inference scenarios rely on extracting relevant information from known data in order to make future predictions. When the underlying stochastic process satisfies certain assumptions, there is a direct mapping between its exact classical and quantum simulators, with the latter asymptotically using less memory. Here we focus on studying whether such quantum advantage persists when those assumptions are not satisfied, and the model is doomed to have imperfect accuracy. By studying the trade-off between accuracy and memory requirements, we show that quantum models can reach the same accuracy with less memory, or alternatively, better accuracy with the same memory. Finally, we discuss the implications of this result for learning tasks.

References in corpus (8)

• The density-matrix renormalization group in the age of matrix product states
• The iTEBD algorithm beyond unitary evolution
• An Algorithm for Pattern Discovery in Time Series
• Formal Algorithms for Transformers
• Memory compression and thermal efficiency of quantum implementations of non-deterministic hidden Markov models
• Statistical Complexity of Quantum Learning
• Quantum coarse-graining for extreme dimension reduction in modelling stochastic temporal dynamics
• Information-Theoretic Reduction of Markov Chains

Cited by in corpus (3)

• Analysis of Quantum Image Representations for Supervised Classification
• Quantum Dimension Reduction of Hidden Markov Models
• Quantum reservoir computing for predicting and characterizing chaotic maps