Predicting quantum dynamical cost landscapes with deep learning

Abstract

State-of-the-art quantum algorithms routinely tune dynamically parametrized cost functionals for combinatorics, machine learning, equation-solving, or energy minimization. However, large search complexity often demands many (noisy) quantum measurements, leading to the increasing use of classical probability models to estimate which areas in the cost functional landscape are of highest interest. Introducing deep learning based modelling of the landscape, we demonstrate an order of magnitude increases in accuracy and speed over state-of-the-art Bayesian methods. Moreover, once trained the deep neural network enables the extraction of information at a much faster rate than conventional numerical simulation. This allows for on-the-fly experimental optimizations and detailed classification of complexity and navigability throughout the phase diagram of the landscape.

12 pages, 8 figures

References in corpus (7)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum computational advantage using photons
• The Magnus expansion and some of its applications
• Quantum Circuit Simplification and Level Compaction
• Exploiting Landscape Geometry to Enhance Quantum Optimal Control
• Linear and logarithmic time compositions of quantum many-body operators
• Searching for quantum optimal controls under severe constraints

Cited by in corpus (15)

• Theory of overparametrization in quantum neural networks
• QuOCS: The Quantum Optimal Control Suite
• Fast, high precision dynamics in quantum optimal control theory
• Optimal Control in Disordered Quantum Systems
• Quantum Gate Generation in Two-Level Open Quantum Systems by Coherent and Incoherent Photons Found with Gradient Search
• Hybrid discrete-continuous compilation of trapped-ion quantum circuits with deep reinforcement learning
• Non-Adiabatic Quantum Optimization for Crossing Quantum Phase Transitions
• Toward a Theory of Phase Transitions in Quantum Control Landscapes
• Phenomenon of a stronger trapping behaviour in $\Lambda$-type quantum systems with symmetry
• Quantum optimal control in quantum technologies. Strategic report on current status, visions and goals for research in Europe
• Control landscapes for high-fidelity generation of C-NOT and C-PHASE gates with coherent and environmental driving
• On optimization of coherent and incoherent controls for two-level quantum systems
• On the detailed structure of quantum control landscape for fast single qubit phase-shift gate generation
• Machine learning for predicting control landscape maps of quantum molecular dynamics: Laser-induced three-dimensional alignment of asymmetric top molecules
• Diverse efficiency of observable optimization for four-level quantum systems with higher-order traps