arXiv subjects

Yusen Wu

Publications and source records attributed to Yusen Wu.

53 records · Page 3Linked to original sources

arXiv2023

A Quantum Federated Learning Framework for Classical Clients

Quantum Federated Learning (QFL) enables collaborative training of a Quantum Machine Learning (QML) model among multiple clients possessing quantum computing capabilities, without the need to share their respective local data. However, the limited availability of quantum computing resources poses a challenge for each client to acquire quantum computing capabilities. This raises a natural question: Can quantum computing capabilities be deployed on the server instead? In this paper, we propose a QFL framework specifically designed for classical clients, referred to as CC-QFL, in response to this question. In each iteration, the collaborative training of the QML model is assisted by the shadow tomography technique, eliminating the need for quantum computing capabilities of clients. Specifically, the server constructs a classical representation of the QML model and transmits it to the clients. The clients encode their local data onto observables and use this classical representation to calculate local gradients. These local gradients are then utilized to update the parameters of the QML model. We evaluate the effectiveness of our framework through extensive numerical simulations using handwritten digit images from the MNIST dataset. Our framework provides valuable insights into QFL, particularly in scenarios where quantum computing resources are scarce.

quant-ph↗

arXiv2023

Tensor-network-assisted variational quantum algorithm

Near-term quantum devices generally suffer from shallow circuit depth and hence limited expressivity due to noise and decoherence. To address this, we propose tensor-network-assisted parametrized quantum circuits, which concatenate a classical tensor-network operator with a quantum circuit to effectively increase the circuit's expressivity without requiring a physically deeper circuit. We present a framework for tensor-network-assisted variational quantum algorithms that can solve quantum many-body problems using shallower quantum circuits. We demonstrate the efficiency of this approach by considering two examples of unitary matrix-product operators and unitary tree tensor networks, showing that they can both be implemented efficiently. Through numerical simulations, we show that the expressivity of these circuits is greatly enhanced with the assistance of tensor networks. We apply our method to two-dimensional Ising models and one-dimensional time-crystal Hamiltonian models with up to 16 qubits and demonstrate that our approach consistently outperforms conventional methods using shallow quantum circuits.

quant-ph↗

arXiv2023

A Joint Gradient and Loss Based Clustered Federated Learning Design

In this paper, a novel clustered FL framework that enables distributed edge devices with non-IID data to independently form several clusters in a distributed manner and implement FL training within each cluster is proposed. In particular, our designed clustered FL algorithm must overcome two challenges associated with FL training. First, the server has limited FL training information (i.e., the parameter server can only obtain the FL model information of each device) and limited computational power for finding the differences among a large amount of devices. Second, each device does not have the data information of other devices for device clustering and can only use global FL model parameters received from the server and its data information to determine its cluster identity, which will increase the difficulty of device clustering. To overcome these two challenges, we propose a joint gradient and loss based distributed clustering method in which each device determines its cluster identity considering the gradient similarity and training loss. The proposed clustering method not only considers how a local FL model of one device contributes to each cluster but also the direction of gradient descent thus improving clustering speed. By delegating clustering decisions to edge devices, each device can fully leverage its private data information to determine its own cluster identity, thereby reducing clustering overhead and improving overall clustering performance. Simulation results demonstrate that our proposed clustered FL algorithm can reduce clustering iterations by up to 99% compared to the existing baseline.

cs.LG↗

arXiv2023

Improving VTE Identification through Adaptive NLP Model Selection and Clinical Expert Rule-based Classifier from Radiology Reports

Rapid and accurate identification of Venous thromboembolism (VTE), a severe cardiovascular condition including deep vein thrombosis (DVT) and pulmonary embolism (PE), is important for effective treatment. Leveraging Natural Language Processing (NLP) on radiology reports, automated methods have shown promising advancements in identifying VTE events from retrospective data cohorts or aiding clinical experts in identifying VTE events from radiology reports. However, effectively training Deep Learning (DL) and the NLP models is challenging due to limited labeled medical text data, the complexity and heterogeneity of radiology reports, and data imbalance. This study proposes novel method combinations of DL methods, along with data augmentation, adaptive pre-trained NLP model selection, and a clinical expert NLP rule-based classifier, to improve the accuracy of VTE identification in unstructured (free-text) radiology reports. Our experimental results demonstrate the model's efficacy, achieving an impressive 97\% accuracy and 97\% F1 score in predicting DVT, and an outstanding 98.3\% accuracy and 98.4\% F1 score in predicting PE. These findings emphasize the model's robustness and its potential to significantly contribute to VTE research.

cs.CL↗

arXiv2023

Trainability Analysis of Quantum Optimization Algorithms from a Bayesian Lens

The Quantum Approximate Optimization Algorithm (QAOA) is an extensively studied variational quantum algorithm utilized for solving optimization problems on near-term quantum devices. A significant focus is placed on determining the effectiveness of training the $n$-qubit QAOA circuit, i.e., whether the optimization error can converge to a constant level as the number of optimization iterations scales polynomially with the number of qubits. In realistic scenarios, the landscape of the corresponding QAOA objective function is generally non-convex and contains numerous local optima. In this work, motivated by the favorable performance of Bayesian optimization in handling non-convex functions, we theoretically investigate the trainability of the QAOA circuit through the lens of the Bayesian approach. This lens considers the corresponding QAOA objective function as a sample drawn from a specific Gaussian process. Specifically, we focus on two scenarios: the noiseless QAOA circuit and the noisy QAOA circuit subjected to local Pauli channels. Our first result demonstrates that the noiseless QAOA circuit with a depth of $\tilde{\mathcal{O}}\left(\sqrt{\log n}\right)$ can be trained efficiently, based on the widely accepted assumption that either the left or right slice of each block in the circuit forms a local 1-design. Furthermore, we show that if each quantum gate is affected by a $q$-strength local Pauli channel with the noise strength range of $1/{\rm poly} (n)$ to 0.1, the noisy QAOA circuit with a depth of $\mathcal{O}\left(\log n/\log(1/q)\right)$ can also be trained efficiently. Our results offer valuable insights into the theoretical performance of quantum optimization algorithms in the noisy intermediate-scale quantum era.

quant-ph↗

arXiv2023

Soft Merging: A Flexible and Robust Soft Model Merging Approach for Enhanced Neural Network Performance

Stochastic Gradient Descent (SGD), a widely used optimization algorithm in deep learning, is often limited to converging to local optima due to the non-convex nature of the problem. Leveraging these local optima to improve model performance remains a challenging task. Given the inherent complexity of neural networks, the simple arithmetic averaging of the obtained local optima models in undesirable results. This paper proposes a {\em soft merging} method that facilitates rapid merging of multiple models, simplifies the merging of specific parts of neural networks, and enhances robustness against malicious models with extreme values. This is achieved by learning gate parameters through a surrogate of the $l_0$ norm using hard concrete distribution without modifying the model weights of the given local optima models. This merging process not only enhances the model performance by converging to a better local optimum, but also minimizes computational costs, offering an efficient and explicit learning process integrated with stochastic gradient descent. Thorough experiments underscore the effectiveness and superior performance of the merged neural networks.

cs.LG↗

arXiv2023

Enabling Quartile-based Estimated-Mean Gradient Aggregation As Baseline for Federated Image Classifications

Federated Learning (FL) has revolutionized how we train deep neural networks by enabling decentralized collaboration while safeguarding sensitive data and improving model performance. However, FL faces two crucial challenges: the diverse nature of data held by individual clients and the vulnerability of the FL system to security breaches. This paper introduces an innovative solution named Estimated Mean Aggregation (EMA) that not only addresses these challenges but also provides a fundamental reference point as a $\mathsf{baseline}$ for advanced aggregation techniques in FL systems. EMA's significance lies in its dual role: enhancing model security by effectively handling malicious outliers through trimmed means and uncovering data heterogeneity to ensure that trained models are adaptable across various client datasets. Through a wealth of experiments, EMA consistently demonstrates high accuracy and area under the curve (AUC) compared to alternative methods, establishing itself as a robust baseline for evaluating the effectiveness and security of FL aggregation methods. EMA's contributions thus offer a crucial step forward in advancing the efficiency, security, and versatility of decentralized deep learning in the context of FL.

cs.CR↗

arXiv2023

Quantum Phase Recognition via Quantum Kernel Methods

The application of quantum computation to accelerate machine learning algorithms is one of the most promising areas of research in quantum algorithms. In this paper, we explore the power of quantum learning algorithms in solving an important class of Quantum Phase Recognition (QPR) problems, which are crucially important in understanding many-particle quantum systems. We prove that, under widely believed complexity theory assumptions, there exists a wide range of QPR problems that cannot be efficiently solved by classical learning algorithms with classical resources. Whereas using a quantum computer, we prove the efficiency and robustness of quantum kernel methods in solving QPR problems through Linear order parameter Observables. We numerically benchmark our algorithm for a variety of problems, including recognizing symmetry-protected topological phases and symmetry-broken phases. Our results highlight the capability of quantum machine learning in predicting such quantum phase transitions in many-particle systems.

quant-ph↗

arXiv2022

Orbital Expansion Variational Quantum Eigensolver: Enabling Efficient Simulation of Molecules with Shallow Quantum Circuit

In the noisy-intermediate-scale-quantum era, Variational Quantum Eigensolver (VQE) is a promising method to study ground state properties in quantum chemistry, materials science, and condensed physics. However, general quantum eigensolvers are lack of systematical improvability, and achieve rigorous convergence is generally hard in practice, especially in solving strong-correlated systems. Here, we propose an Orbital Expansion VQE~(OE-VQE) framework to construct an efficient convergence path. The path starts from a highly correlated compact active space and rapidly expands and converges to the ground state, enabling simulating ground states with much shallower quantum circuits. We benchmark the OE-VQE on a series of typical molecules including H$_{6}$-chain, H$_{10}$-ring and N$_2$, and the simulation results show that proposed convergence paths dramatically enhance the performance of general quantum eigensolvers.

quant-ph↗

arXiv2022

MixNN: A design for protecting deep learning models

In this paper, we propose a novel design, called MixNN, for protecting deep learning model structure and parameters. The layers in a deep learning model of MixNN are fully decentralized. It hides communication address, layer parameters and operations, and forward as well as backward message flows among non-adjacent layers using the ideas from mix networks. MixNN has following advantages: 1) an adversary cannot fully control all layers of a model including the structure and parameters, 2) even some layers may collude but they cannot tamper with other honest layers, 3) model privacy is preserved in the training phase. We provide detailed descriptions for deployment. In one classification experiment, we compared a neural network deployed in a virtual machine with the same one using the MixNN design on the AWS EC2. The result shows that our MixNN retains less than 0.001 difference in terms of classification accuracy, while the whole running time of MixNN is about 7.5 times slower than the one running on a single virtual machine.

cs.DC↗

arXiv2021

Estimating Gibbs partition function with quantumClifford sampling

The partition function is an essential quantity in statistical mechanics, and its accurate computation is a key component of any statistical analysis of quantum system and phenomenon. However, for interacting many-body quantum systems, its calculation generally involves summing over an exponential number of terms and can thus quickly grow to be intractable. Accurately and efficiently estimating the partition function of its corresponding system Hamiltonian then becomes the key in solving quantum many-body problems. In this paper we develop a hybrid quantum-classical algorithm to estimate the partition function, utilising a novel Clifford sampling technique. Note that previous works on quantum estimation of partition functions require $\mathcal{O}(1/ε\sqrtΔ)$-depth quantum circuits~\cite{Arunachalam2020Gibbs, Ashley2015Gibbs}, where $Δ$ is the minimum spectral gap of stochastic matrices and $ε$ is the multiplicative error. Our algorithm requires only a shallow $\mathcal{O}(1)$-depth quantum circuit, repeated $\mathcal{O}(1/ε^2)$ times, to provide a comparable $ε$ approximation. Shallow-depth quantum circuits are considered vitally important for currently available NISQ (Noisy Intermediate-Scale Quantum) devices.

quant-ph↗

arXiv2021

Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning

Adversarial attacks attempt to disrupt the training, retraining and utilizing of artificial intelligence and machine learning models in large-scale distributed machine learning systems. This causes security risks on its prediction outcome. For example, attackers attempt to poison the model by either presenting inaccurate misrepresentative data or altering the models' parameters. In addition, Byzantine faults including software, hardware, network issues occur in distributed systems which also lead to a negative impact on the prediction outcome. In this paper, we propose a novel distributed training algorithm, partial synchronous stochastic gradient descent (ParSGD), which defends adversarial attacks and/or tolerates Byzantine faults. We demonstrate the effectiveness of our algorithm under three common adversarial attacks again the ML models and a Byzantine fault during the training phase. Our results show that using ParSGD, ML models can still produce accurate predictions as if it is not being attacked nor having failures at all when almost half of the nodes are being compromised or failed. We will report the experimental evaluations of ParSGD in comparison with other algorithms.

cs.CR↗

arXiv2020

Variational Quantum algorithm for Poisson equation

The Poisson equation has wide applications in many areas of science and engineering. Although there are some quantum algorithms that can efficiently solve the Poisson equation, they generally require a fault-tolerant quantum computer which is beyond the current technology. In this paper, we propose a Variational Quantum Algorithm (VQA) to solve the Poisson equation, which can be executed on Noise Intermediate-Scale Quantum (NISQ) devices. In detail, we first adopt the finite difference method to transform the Poisson equation into a linear system. Then, according to the special structure of the linear system, we find an explicit tensor product decomposition, with only $2\log n+1$ items, of its coefficient matrix under a specific set of simple operators, where $n$ is the dimension of the coefficient matrix. This implies that the proposed VQA only needs $O(\log n)$ measurements, which dramatically reduce quantum resources. Additionally, we perform quantum Bell measurements to efficiently evaluate the expectation values of simple operators. Numerical experiments demonstrate that our algorithm can effectively solve the Poisson equation.

quant-ph↗

arXiv2020

Weak bi-center and critical period bifurcations of a $Z_2$-Equivariant quintic system

With the help of computer algebra system-\textsc{Mathematica}, this paper considers the weak center problem and local critical periods for bi-center of a $Z_2$-Equivariant quintic system with eight parameters. The order of weak bi-center is identified and the exact maximum number of bifurcation of critical periods generated from the bi-center is given via the combination of symbolic calculation and numerical analysis.

math.DS↗

arXiv2020

Quantum restricted Boltzmann machine universal for quantum computation

The challenge posed by the many-body problem in quantum physics originates from the difficulty of describing the nontrivial correlations encoded in the many-body wave functions with high complexity. Quantum neural network provides a powerful tool to represent the large-scale wave function, which has aroused widespread concern in the quantum superiority era. A significant open problem is what exactly the representational power boundary of the single-layer quantum neural network is. In this paper, we design a 2-local Hamiltonian and then give a kind of Quantum Restricted Boltzmann Machine (QRBM, i.e. single-layer quantum neural network) based on it. The proposed QRBM has the following two salient features. (1) It is proved universal for implementing quantum computation tasks. (2) It can be efficiently implemented on the Noisy Intermediate-Scale Quantum (NISQ) devices. We successfully utilize the proposed QRBM to compute the wave functions for the notable cases of physical interest including the ground state as well as the Gibbs state (thermal state) of molecules on the superconducting quantum chip. The experimental results illustrate the proposed QRBM can compute the above wave functions with an acceptable error.

quant-ph↗

arXiv2019

Bayesian machine learning for Boltzmann machine in quantum-enhanced feature spaces

Bayesian learning is ubiquitous for implementing classification and regression tasks, however, it is accompanied by computationally intractable limitations when the feature spaces become extremely large. Aiming to solve this problem, we develop a quantum bayesian learning framework of the restricted Boltzmann machine in the quantum-enhanced feature spaces. Our framework provides the encoding phase to map the real data and Boltzmann weight onto the quantum feature spaces and the training phase to learn an optimal inference function. Specifically, the training phase provides a physical quantity to measure the posterior distribution in quantum feature spaces, and this measure is utilized to design the quantum maximum a posterior (QMAP) algorithm and the quantum predictive distribution estimator (QPDE). It is shown that both quantum algorithms achieve exponential speed-up over their classical counterparts. Furthermore, it is interesting to note that our framework can figure out the classical bayesian learning tasks, i.e. processing the classical data and outputting corresponding classical labels. And a simulation, which is performed on an open-source software framework for quantum computing, illustrates that our algorithms show almost the same classification performance compared to their classical counterparts. Noting that the proposed quantum algorithms utilize the shallow circuit, our work is expected to be implemented on the noisy intermediate-scale quantum (NISQ) devices, and is one of the promising candidates to achieve quantum supremacy.

quant-ph↗

arXiv2019

Quantum Conditional Random Field

Conditional random field (CRF) is an important probabilistic machine learning model for labeling sequential data, which is widely utilized in natural language processing, bioinformatics and computer vision. However, training the CRF model is computationally intractable when large scale training samples are processed. Since little work has been done for labeling sequential data in the quantum settings, we in this paper construct a quantum CRF (QCRF) model by introducing well-defined Hamiltonians and measurements, and present a quantum algorithm to train this model. It is shown that the algorithm achieves an exponential speed-up over its classical counterpart. Furthermore, we also demonstrate that the QCRF model possesses higher Vapnik Chervonenkis dimension than the classical CRF model, which means QCRF is equipped with a higher learning ability.

quant-ph↗