Data-Centric Machine Learning in Quantum Information Science
arXiv:2201.09134 · doi:10.1088/2632-2153/ac9036
Abstract
We propose a series of data-centric heuristics for improving the performance of machine learning systems when applied to problems in quantum information science. In particular, we consider how systematic engineering of training sets can significantly enhance the accuracy of pre-trained neural networks used for quantum state reconstruction without altering the underlying architecture. We find that it is not always optimal to engineer training sets to exactly match the expected distribution of a target scenario, and instead, performance can be further improved by biasing the training set to be slightly more mixed than the target. This is due to the heterogeneity in the number of free variables required to describe states of different purity, and as a result, overall accuracy of the network improves when training sets of a fixed size focus on states with the least constrained free variables. For further clarity, we also include a "toy model" demonstration of how spurious correlations can inadvertently enter synthetic data sets used for training, how the performance of systems trained with these correlations can degrade dramatically, and how the inclusion of even relatively few counterexamples can effectively remedy such problems.
References in corpus (40)
- Separability Criterion for Density Matrices
- Separability of Mixed States: Necessary and Sufficient Conditions
- Machine learning and the physical sciences
- Entanglement detection
- On the Measurement of Qubits
- Predicting Many Properties of a Quantum System from Very Few Measurements
- Power of data in quantum machine learning
- Induced measures in the space of mixed quantum states
- Maximal entanglement versus entropy for mixed quantum states
- Maximizing the entanglement of two mixed qubits
- Reinforcement Learning in Different Phases of Quantum Control
- Maximum Likelihood, Minimum Effort
- On the volume of the set of mixed entangled states II
- Turbulence correction with artificial neural networks
- Average fidelity between random quantum states
- When does reinforcement learning stand out in quantum control? A comparative study on state preparation
- A practical and efficient approach for Bayesian quantum state estimation
- A Separability-Entanglement Classifier via Machine Learning
- A Reconfigurable Quantum Local Area Network Over Deployed Fiber
- On the use of deep neural networks in optical communications
- Generalizable control for quantum parameter estimation through reinforcement learning
- Coherent Transport of Quantum States by Deep Reinforcement Learning
- Machine learning assisted quantum state estimation
- Random Bures mixed states and the distribution of their purity
- Adaptive bandwidth management for entanglement distribution in quantum networks
- Machine Learning for Optimal Parameter Prediction in Quantum Key Distribution
- Entanglement Classification via Neural Network Quantum States
- Machine Learning meets Quantum Foundations: A Brief Survey
- Fully Arbitrary Control of Frequency-Bin Qubits
- Generative Machine Learning for Robust Free-Space Communication
- Breaking Adiabatic Quantum Control with Deep Learning
- Improving the dynamics of quantum sensors with reinforcement learning
- Learning Temporal Quantum Tomography
- A Bayesian analysis of classical shadows
- On the experimental feasibility of quantum state reconstruction via machine learning
- Quantum-tailored machine-learning characterization of a superconducting qubit
- Pseudo-Bayesian Quantum Tomography with Rank-adaptation
- Improving application performance with biased distributions of quantum states
- Neural-network-based parameter estimation for quantum detection
- Coherent Optical Communications Enhanced by Machine Intelligence