Resource frugal optimizer for quantum machine learning
arXiv:2211.04965 · doi:10.1088/2058-9565/acef55
Abstract
Quantum-enhanced data science, also known as quantum machine learning (QML), is of growing interest as an application of near-term quantum computers. Variational QML algorithms have the potential to solve practical problems on real hardware, particularly when involving quantum data. However, training these algorithms can be challenging and calls for tailored optimization procedures. Specifically, QML applications can require a large shot-count overhead due to the large datasets involved. In this work, we advocate for simultaneous random sampling over both the dataset as well as the measurement operators that define the loss function. We consider a highly general loss function that encompasses many QML applications, and we show how to construct an unbiased estimator of its gradient. This allows us to propose a shot-frugal gradient descent optimizer called Refoqus (REsource Frugal Optimizer for QUantum Stochastic gradient descent). Our numerics indicate that Refoqus can save several orders of magnitude in shot cost, even relative to optimizers that sample over measurement operators alone.
arXiv comment22 pages, 6 figures - extra quantum autoencoder results added - extra affiliation
References in corpus (46)
- Quantum Machine Learning
- Barren plateaus in quantum neural network training landscapes
- Quantum Circuit Learning
- Quantum Convolutional Neural Networks
- Quantum principal component analysis
- An introduction to quantum machine learning
- Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
- Evaluating analytic gradients on quantum hardware
- Circuit-centric quantum classifiers
- The power of quantum neural networks
- Noise-Induced Barren Plateaus in Variational Quantum Algorithms
- Towards Practical Quantum Variational Algorithms
- Efficient Learning for Deep Quantum Neural Networks
- The quest for a Quantum Neural Network
- Connecting ansatz expressibility to gradient magnitudes and barren plateaus
- Practical Quantum Error Mitigation for Near-Future Applications
- Hybrid quantum-classical algorithms and quantum error mitigation
- Quantum autoencoders for efficient compression of quantum data
- Quantum Natural Gradient
- Training variational quantum algorithms is NP-hard
- Absence of Barren Plateaus in Quantum Convolutional Neural Networks
- Differentiable Learning of Quantum Circuit Born Machine
- Low-cost error mitigation by symmetry verification
- Learning-based quantum error mitigation
- Variational Fast Forwarding for Quantum Simulation Beyond the Coherence Time
- Effect of barren plateaus on gradient-free optimization
- Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
- Stochastic gradient descent for hybrid quantum-classical optimization
- Variational Quantum State Diagonalization
- Sequential minimal optimization for quantum-classical hybrid algorithms
- Trainability of Dissipative Perceptron-Based Quantum Neural Networks
- Variational Quantum State Eigensolver
- Barren plateaus preclude learning scramblers
- An Adaptive Optimizer for Measurement-Frugal Variational Algorithms
- Quantum autoencoders to denoise quantum data
- On barren plateaus and cost function locality in variational quantum algorithms
- Performance comparison of optimization methods on variational quantum algorithms
- Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
- Unified approach to data-driven quantum error mitigation
- Error mitigation for variational quantum algorithms through mid-circuit measurements
- Unbiased and Efficient Log-Likelihood Estimation with Inverse Binomial Sampling
- To quantum or not to quantum: towards algorithm selection in near-term quantum optimization
- Stochastic Gradient Line Bayesian Optimization for Efficient Noise-Robust Optimization of Parameterized Quantum Circuits
- Analyzing variational quantum landscapes with information content
- Quark: A Gradient-Free Quantum Learning Framework for Classification Tasks
- Unsupervised strategies for identifying optimal parameters in Quantum Approximate Optimization Algorithm