Deep learning optimal quantum annealing schedules for random Ising models

Abstract

A crucial step in the race towards quantum advantage is optimizing quantum annealing using ad-hoc annealing schedules. Motivated by recent progress in the field, we propose to employ long-short term memory (LSTM) neural networks to automate the search for optimal annealing schedules for random Ising models on regular graphs. By training our network using locally-adiabatic annealing paths, we are able to predict optimal annealing schedules for unseen instances and even larger graphs than those used for training.

arXiv comment10 pages, 8 figures

References in corpus (64)

• Adam: A Method for Stochastic Optimization
• A Comprehensive Survey on Graph Neural Networks
• Quantum Computing in the NISQ era and beyond
• Quantum Mechanics helps in searching for a needle in a haystack
• Ising formulations of many NP problems
• Quantum Annealing in the Transverse Ising Model
• QuTiP: An open-source Python framework for the dynamics of open quantum systems
• A Quantum Approximate Optimization Algorithm
• Adiabatic Quantum Computing
• Shortcuts to adiabaticity: concepts, methods, and applications
• Theory of Quantum Annealing of an Ising Spin Glass
• Quantum Search by Local Adiabatic Evolution
• Defining and detecting quantum speedup
• Quantum Computation by Adiabatic Evolution
• Shortcuts to adiabaticity by counter-diabatic driving
• Perspectives of quantum annealing: Methods and implementations
• Mathematical Foundation of Quantum Annealing
• Bounds for the adiabatic approximation with applications to quantum computation
• Minimizing irreversible losses in quantum systems by local counter-diabatic driving
• Reverse Quantum Annealing Approach to Portfolio Optimization Problems
• A case study in programming a quantum annealer for hard operational planning problems
• Floquet-engineering counterdiabatic protocols in quantum many-body systems
• Quantum annealing of the Traveling Salesman Problem
• Quantum Speedup by Quantum Annealing
• Quantum annealing versus classical machine learning applied to a simplified computational biology problem
• Decoherence in adiabatic quantum computation
• Searching for quantum speedup in quasistatic quantum annealers
• Prospects for Quantum Enhancement with Diabatic Quantum Annealing
• Quantum annealing with antiferromagnetic fluctuations
• Optimal Protocols in Quantum Annealing and QAOA Problems
• Energy gaps in quantum first-order mean-field-like transitions: The problems that quantum annealing cannot solve
• Power of Pausing: Advancing Understanding of Thermalization in Experimental Quantum Annealers
• Reverse annealing for the fully connected $p$-spin model
• Optimization by Quantum Annealing: Lessons from hard 3-SAT cases
• Experimental determination of Ramsey numbers
• Quantum Annealing for Constrained Optimization
• Dynamics of reverse annealing for the fully-connected $p$-spin model
• A deceptive step towards quantum speedup detection
• Different Strategies for Optimization Using the Quantum Adiabatic Algorithm
• Reverse quantum annealing of the $p$-spin model with relaxation
• Counterdiabatic driving in the quantum annealing of the $p$-spin model: a variational approach
• Improving quantum annealing of the ferromagnetic $p$-spin model through pausing
• Role of Non-stoquastic Catalysts in Quantum Adiabatic Optimization
• Non-ergodic delocalized states for efficient population transfer within a narrow band of the energy landscape
• Quantum annealing of the random-field Ising model by transverse ferromagnetic interactions
• Genetic optimization of quantum annealing
• Why and when is pausing beneficial in quantum annealing?
• A dissipative environment may improve the quantum annealing performances of the ferromagnetic p-spin model
• Charged particle tracking with quantum annealing-inspired optimization
• Variational optimization of the quantum annealing schedule for the Lechner-Hauke-Zoller scheme
• Optimal quantum annealing: A variational shortcut to adiabaticity approach
• Optimal Control for Closed and Open System Quantum Optimization
• Variationally Scheduled Quantum Simulation
• Deep Learning of Quantum Many-Body Dynamics via Random Driving
• Assessment of Quantum Annealing for the Construction of Satisfiability Filters
• Speeding up adiabatic passage with an optimal modified Roland-Cerf protocol
• Ferromagnetically shifting the power of pausing
• Standard quantum annealing outperforms adiabatic reverse annealing with decoherence
• Quantum Speed-Up at Zero Temperature via Coherent Catalysis
• Diabatic Quantum Annealing for the Frustrated Ring Model
• Customized quantum annealing schedules
• Deep recurrent networks predicting the gap evolution in adiabatic quantum computing
• Optimization in random field Ising models by quantum annealing
• Optimal quantum control with digitized Quantum Annealing

Cited by in corpus (6)

• A comprehensive review on developments of synthetic dimensions
• Designing Quantum Annealing Schedules using Bayesian Optimization
• Diabatic Quantum Annealing for the Frustrated Ring Model
• Convergence of Digitized-Counterdiabatic QAOA: circuit depth versus free parameters
• Noise Effects on Diabatic Quantum Annealing Protocols
• Hidden local adiabatic ramp in the modulated time evolution and the quantum approximate optimization algorithm