Haimeng Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Haimeng Zhao has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Bin Yang
School of Artificial Intelligence and Robotics, Hunan University, Changsha, China
1 shared publication - Dong-Ling Deng
Tsinghua University
1 shared publication - Fangyu Li
Beijing University of Technology
1 shared publication - Filippo Girardi
Scuola Normale Superiore Piazza dei Cavalieri 7 56126 Pisa Italy
1 shared publication - Francesco Anna Mele
Scuola Normale Superiore and Istituto Nanoscienze, Piazza dei Cavalieri 7
1 shared publication - Hsin-Yuan Huang
California Institute of Technology
1 shared publication
Latest Publications
- Open Access
Random Stinespring superchannel: converting channel queries into dilation isometry queries
The recently introduced random purification channel, which converts $n$ copies of an arbitrary mixed quantum state into $n$ copies of the same uniformly random purification, has emerged as a powerful tool in quantum information theory. Motivated by this development, we introduce a channel-level analogue, which we call the random Stinespring superchannel. This consists in a procedure to transform $n$ parallel queries of an arbitrary quantum channel into $n$ parallel queries of the same uniformly random Stinespring isometry, via universal encoding and decoding operations that are efficiently implementable. When the channel is promised to have Choi rank at most $r$, the procedure can be tailored to yield a Stinespring environment of dimension $r$. As a consequence, quantum channel learning reduces to isometry learning, yielding a simple channel learning algorithm, based on existing isometry learning protocols, that matches the performance of the two recently proposed channel tomography algorithms. Complementarily, whereas the optimality of these algorithms had previously been established only up to a logarithmic factor in the dimension, we close this gap by removing this logarithmic factor from the lower bound. Taken together, our results fully establish the optimality of these recently introduced channel learning algorithms, showing that the optimal query complexity of learning a quantum channel with input dimension $d_A$, output dimension $d_B$, and Choi rank $r$ is $Θ(d_A d_B r)$.Open AccessRandom Stinespring superchannel: converting channel queries into dilation isometry queries
The recently introduced random purification channel, which converts $n$ copies of an arbitrary mixed quantum state into $n$ copies of the same uniformly random purification, has emerged as a powerful tool in quantum information theory. Motivated by this development, we introduce a channel-level analogue, which we call the random Stinespring superchannel. This consists in a procedure to transform $n$ parallel queries of an arbitrary quantum channel into $n$ parallel queries of the same uniformly random Stinespring isometry, via universal encoding and decoding operations that are efficiently implementable. When the channel is promised to have Choi rank at most $r$, the procedure can be tailored to yield a Stinespring environment of dimension $r$. As a consequence, quantum channel learning reduces to isometry learning, yielding a simple channel learning algorithm, based on existing isometry learning protocols, that matches the performance of the two recently proposed channel tomography algorithms. Complementarily, whereas the optimality of these algorithms had previously been established only up to a logarithmic factor in the dimension, we close this gap by removing this logarithmic factor from the lower bound. Taken together, our results fully establish the optimality of these recently introduced channel learning algorithms, showing that the optimal query complexity of learning a quantum channel with input dimension $d_A$, output dimension $d_B$, and Choi rank $r$ is $Θ(d_A d_B r)$. - Open Access
- 29 July 2025
- Published by Springer Nature in npj Quantum Information
- Vol. 11 (1) , 1-8
Entanglement-induced provable and robust quantum learning advantages
- 29 July 2025
- Published by Springer Nature in npj Quantum Information
- Vol. 11 (1) , 1-8
Open AccessEntanglement-induced provable and robust quantum learning advantages
- Open Access
- 16 October 2024
- Published by American Physical Society (APS) in PRX Quantum
- Vol. 5 (4)
Learning Quantum States and Unitaries of Bounded Gate Complexity
While quantum state tomography is notoriously hard, most states hold little interest to practically minded tomographers. Given that states and unitaries appearing in nature are of bounded gate complexity, it is natural to ask if efficient learning becomes possible. In this work, we prove that to learn a state generated by a quantum circuit with G two-qubit gates to a small trace distance, a sample complexity scaling linearly in G is necessary and sufficient. We also prove that the optimal query complexity to learn a unitary generated by G gates to a small average-case error scales linearly in G . While sample-efficient learning can be achieved, we show that under reasonable cryptographic conjectures, the computational complexity for learning states and unitaries of gate complexity G must scale exponentially in G . We illustrate how these results establish fundamental limitations on the expressivity of quantum machine-learning models and provide new perspectives on no-free-lunch theorems in unitary learning. Together, our results answer how the complexity of learning quantum states and unitaries relate to the complexity of creating these states and unitaries. Published by the American Physical Society 2024
- 16 October 2024
- Published by American Physical Society (APS) in PRX Quantum
- Vol. 5 (4)
Open AccessLearning Quantum States and Unitaries of Bounded Gate Complexity
While quantum state tomography is notoriously hard, most states hold little interest to practically minded tomographers. Given that states and unitaries appearing in nature are of bounded gate complexity, it is natural to ask if efficient learning becomes possible. In this work, we prove that to learn a state generated by a quantum circuit with G two-qubit gates to a small trace distance, a sample complexity scaling linearly in G is necessary and sufficient. We also prove that the optimal query complexity to learn a unitary generated by G gates to a small average-case error scales linearly in G . While sample-efficient learning can be achieved, we show that under reasonable cryptographic conjectures, the computational complexity for learning states and unitaries of gate complexity G must scale exponentially in G . We illustrate how these results establish fundamental limitations on the expressivity of quantum machine-learning models and provide new perspectives on no-free-lunch theorems in unitary learning. Together, our results answer how the complexity of learning quantum states and unitaries relate to the complexity of creating these states and unitaries. Published by the American Physical Society 2024
- Open Access
- 9 January 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (2) , 1-27
CPS Attack Detection under Limited Local Information in Cyber Security: An Ensemble Multi-Node Multi-Class Classification Approach
Cybersecurity breaches are common anomalies for distributed cyber-physical systems (CPS). However, the cyber security breach classification is still a difficult problem, even using cutting-edge artificial intelligence (AI) approaches. In this article, we study a multi-class classification problem in cyber security for attack detection. A challenging multi-node data-censoring case is considered. In such a case, data within each data center/node cannot be shared while the local data is incomplete. Particularly, local nodes contain only a part of the multiple classes. In order to train a global multi-class classifier without sharing the raw data across all nodes, we design a multi-node multi-class classification ensemble approach which is the main result of our study. By gathering the estimated parameters of the binary classifiers and data densities from each local node, the missing information for each local node is completed to build the global multi-class classifier. Numerical experiments are given to validate the effectiveness of the proposed approach under the multi-node data-censoring case. Under such a case, we even show the out-performance of the proposed approach over the full-data approach.
- 9 January 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (2) , 1-27
Open AccessCPS Attack Detection under Limited Local Information in Cyber Security: An Ensemble Multi-Node Multi-Class Classification Approach
Cybersecurity breaches are common anomalies for distributed cyber-physical systems (CPS). However, the cyber security breach classification is still a difficult problem, even using cutting-edge artificial intelligence (AI) approaches. In this article, we study a multi-class classification problem in cyber security for attack detection. A challenging multi-node data-censoring case is considered. In such a case, data within each data center/node cannot be shared while the local data is incomplete. Particularly, local nodes contain only a part of the multiple classes. In order to train a global multi-class classifier without sharing the raw data across all nodes, we design a multi-node multi-class classification ensemble approach which is the main result of our study. By gathering the estimated parameters of the binary classifiers and data densities from each local node, the missing information for each local node is completed to build the global multi-class classifier. Numerical experiments are given to validate the effectiveness of the proposed approach under the multi-node data-censoring case. Under such a case, we even show the out-performance of the proposed approach over the full-data approach.
- Open Access
Non-IID Quantum Federated Learning with One-shot Communication Complexity
Federated learning refers to the task of machine learning based on decentralized data from multiple clients with secured data privacy. Recent studies show that quantum algorithms can be exploited to boost its performance. However, when the clients' data are not independent and identically distributed (IID), the performance of conventional federated algorithms is known to deteriorate. In this work, we explore the non-IID issue in quantum federated learning with both theoretical and numerical analysis. We further prove that a global quantum channel can be exactly decomposed into local channels trained by each client with the help of local density estimators. This observation leads to a general framework for quantum federated learning on non-IID data with one-shot communication complexity. Numerical simulations show that the proposed algorithm outperforms the conventional ones significantly under non-IID settings.
Open AccessNon-IID Quantum Federated Learning with One-shot Communication Complexity
Federated learning refers to the task of machine learning based on decentralized data from multiple clients with secured data privacy. Recent studies show that quantum algorithms can be exploited to boost its performance. However, when the clients' data are not independent and identically distributed (IID), the performance of conventional federated algorithms is known to deteriorate. In this work, we explore the non-IID issue in quantum federated learning with both theoretical and numerical analysis. We further prove that a global quantum channel can be exactly decomposed into local channels trained by each client with the help of local density estimators. This observation leads to a general framework for quantum federated learning on non-IID data with one-shot communication complexity. Numerical simulations show that the proposed algorithm outperforms the conventional ones significantly under non-IID settings.
- 18 January 2023
- Published by Springer Nature in Quantum Machine Intelligence
- Vol. 5 (1) , 1-11
Non-IID quantum federated learning with one-shot communication complexity
- 18 January 2023
- Published by Springer Nature in Quantum Machine Intelligence
- Vol. 5 (1) , 1-11
Non-IID quantum federated learning with one-shot communication complexity
- Open Access
- 14 October 2022
- Published by American Astronomical Society in The Astronomical Journal
- Vol. 164 (5) , 192
MAGIC: Microlensing Analysis Guided by Intelligent Computation
The modeling of binary microlensing light curves via the standard sampling-based method can be challenging, because of the time-consuming light-curve computation and the pathological likelihood landscape in the high-dimensional parameter space. In this work, we present MAGIC, which is a machine-learning framework to efficiently and accurately infer the microlensing parameters of binary events with realistic data quality. In MAGIC, binary microlensing parameters are divided into two groups and inferred separately with different neural networks. The key feature of MAGIC is the introduction of a neural controlled differential equation, which provides the capability to handle light curves with irregular sampling and large data gaps. Based on simulated light curves, we show that MAGIC can achieve fractional uncertainties of a few percent on the binary mass ratio and separation. We also test MAGIC on a real microlensing event. MAGIC is able to locate degenerate solutions even when large data gaps are introduced. As irregular samplings are common in astronomical surveys, our method also has implications for other studies that involve time series.
- 14 October 2022
- Published by American Astronomical Society in The Astronomical Journal
- Vol. 164 (5) , 192
Open AccessMAGIC: Microlensing Analysis Guided by Intelligent Computation
The modeling of binary microlensing light curves via the standard sampling-based method can be challenging, because of the time-consuming light-curve computation and the pathological likelihood landscape in the high-dimensional parameter space. In this work, we present MAGIC, which is a machine-learning framework to efficiently and accurately infer the microlensing parameters of binary events with realistic data quality. In MAGIC, binary microlensing parameters are divided into two groups and inferred separately with different neural networks. The key feature of MAGIC is the introduction of a neural controlled differential equation, which provides the capability to handle light curves with irregular sampling and large data gaps. Based on simulated light curves, we show that MAGIC can achieve fractional uncertainties of a few percent on the binary mass ratio and separation. We also test MAGIC on a real microlensing event. MAGIC is able to locate degenerate solutions even when large data gaps are introduced. As irregular samplings are common in astronomical surveys, our method also has implications for other studies that involve time series.
- 25 October 2018
- Published by Taylor & Francis in Journal of Spatial Science
- Vol. 65 (3) , 445-454
A polarized reflectance model for remote sensing of densely vegetated surfaces
In this paper, we propose a modified model which takes the variation of leaf orientation in zenithal space into consideration. It is special because of the linkage between the parameterization of leaf inclination angle and polarized reflectance modelling. The modified model is compared to the Rondeaux-Herman model, the Nadal-Bréon model and a one-parametric linear model using remotely sensed polarized data which was obtained by the Research Scanning Polarimeter (RSP) over Oklahoma on 16 September 2005. The comparison suggests the modified model accurately captures the polarized reflectance of dense vegetation and works more precisely than the other models.
- 25 October 2018
- Published by Taylor & Francis in Journal of Spatial Science
- Vol. 65 (3) , 445-454
A polarized reflectance model for remote sensing of densely vegetated surfaces
In this paper, we propose a modified model which takes the variation of leaf orientation in zenithal space into consideration. It is special because of the linkage between the parameterization of leaf inclination angle and polarized reflectance modelling. The modified model is compared to the Rondeaux-Herman model, the Nadal-Bréon model and a one-parametric linear model using remotely sensed polarized data which was obtained by the Research Scanning Polarimeter (RSP) over Oklahoma on 16 September 2005. The comparison suggests the modified model accurately captures the polarized reflectance of dense vegetation and works more precisely than the other models.