On exploring the potential of quantum auto-encoder for learning quantum systems
arXiv:2106.15432
Abstract
The frequent interactions between quantum computing and machine learning revolutionize both fields. One prototypical achievement is the quantum auto-encoder (QAE), as the leading strategy to relieve the curse of dimensionality ubiquitous in the quantum world. Despite its attractive capabilities, practical applications of QAE have yet largely unexplored. To narrow this knowledge gap, here we devise three effective QAE-based learning protocols to address three classically computational hard learning problems when learning quantum systems, which are low-rank state fidelity estimation, quantum Fisher information estimation, and Gibbs state preparation. Attributed to the versatility of QAE, our proposals can be readily executed on near-term quantum machines. Besides, we analyze the error bounds of the trained protocols and showcase the necessary conditions to provide practical utility from the perspective of complexity theory. We conduct numerical simulations to confirm the effectiveness of the proposed three protocols. Our work sheds new light on developing advanced quantum learning algorithms to accomplish hard quantum physics and quantum information processing tasks.
Accepted to IEEE Transactions on Neural Networks and Learning Systems
References in corpus (40)
- Advances in Quantum Metrology
- Quantum metrology
- Barren plateaus in quantum neural network training landscapes
- Quantum machine learning in feature Hilbert spaces
- Quantum Circuit Learning
- Machine learning phases of matter
- Error mitigation for short-depth quantum circuits
- Quantum state tomography via compressed sensing
- Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
- Evaluating analytic gradients on quantum hardware
- Efficient Learning for Deep Quantum Neural Networks
- Hybrid Quantum-Classical Hierarchy for Mitigation of Decoherence and Determination of Excited States
- Robust data encodings for quantum classifiers
- The computational complexity of PEPS
- Maximum Likelihood, Minimum Effort
- Sampling from the thermal quantum Gibbs state and evaluating partition functions with a quantum computer
- Variational Quantum State Diagonalization
- Frequency-Dependent Squeezing for Advanced LIGO
- Sample-optimal tomography of quantum states
- Supervised quantum machine learning models are kernel methods
- Training Quantum Embedding Kernels on Near-Term Quantum Computers
- Introduction to quantum Fisher information
- Efficient measure for the expressivity of variational quantum algorithms
- Quantum autoencoders to denoise quantum data
- Experimental Realization of a Quantum Autoencoder: The Compression of Qutrits via Machine Learning
- Towards understanding the power of quantum kernels in the NISQ era
- Variational Quantum Algorithm for Estimating the Quantum Fisher Information
- Efficient estimation of nearly sparse many-body quantum Hamiltonians
- Learning temporal data with variational quantum recurrent neural network
- Impossibility of Classically Simulating One-Clean-Qubit Computation
- Quantum Data Compression of a Qubit Ensemble
- Realization of a quantum autoencoder for lossless compression of quantum data
- Entanglement spectroscopy with a depth-two quantum circuit
- Experimental quantum kernel machine learning with nuclear spins in a solid
- Toward Trainability of Quantum Neural Networks
- A Grover-search Based Quantum Learning Scheme for Classification
- Generic detection-based error-mitigation using quantum autoencoders
- Variational quantum Gibbs state preparation with a truncated Taylor series
- Variational Quantum Algorithms for Trace Distance and Fidelity Estimation
- The dilemma of quantum neural networks