arXiv subjects

Kaixuan Huang

Publications and source records attributed to Kaixuan Huang.

78 records · Page 5Linked to original sources

arXiv2021

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

Federated Learning (FL) coordinates with numerous heterogeneous devices to collaboratively train a shared model while preserving user privacy. Despite its multiple advantages, FL faces new challenges. One challenge arises when devices drop out of the training process beyond the control of the central server. In this case, the convergence of popular FL algorithms such as FedAvg is severely influenced by the straggling devices. To tackle this challenge, we study federated learning algorithms under arbitrary device unavailability and propose an algorithm named Memory-augmented Impatient Federated Averaging (MIFA). Our algorithm efficiently avoids excessive latency induced by inactive devices, and corrects the gradient bias using the memorized latest updates from the devices. We prove that MIFA achieves minimax optimal convergence rates on non-i.i.d. data for both strongly convex and non-convex smooth functions. We also provide an explicit characterization of the improvement over baseline algorithms through a case study, and validate the results by numerical experiments on real-world datasets.

cs.LG↗

arXiv2021

Metrological characterisation of non-Gaussian entangled states of superconducting qubits

Multipartite entangled states are significant resources for both quantum information processing and quantum metrology. In particular, non-Gaussian entangled states are predicted to achieve a higher sensitivity of precision measurements than Gaussian states. On the basis of metrological sensitivity, the conventional linear Ramsey squeezing parameter (RSP) efficiently characterises the Gaussian entangled atomic states but fails for much wider classes of highly sensitive non-Gaussian states. These complex non-Gaussian entangled states can be classified by the nonlinear squeezing parameter (NLSP), as a generalisation of the RSP with respect to nonlinear observables, and identified via the Fisher information. However, the NLSP has never been measured experimentally. Using a 19-qubit programmable superconducting processor, here we report the characterisation of multiparticle entangled states generated during its nonlinear dynamics. First, selecting 10 qubits, we measure the RSP and the NLSP by single-shot readouts of collective spin operators in several different directions. Then, by extracting the Fisher information of the time-evolved state of all 19 qubits, we observe a large metrological gain of 9.89$^{+0.28}_{-0.29}$ dB over the standard quantum limit, indicating a high level of multiparticle entanglement for quantum-enhanced phase sensitivity. Benefiting from high-fidelity full controls and addressable single-shot readouts, the superconducting processor with interconnected qubits provides an ideal platform for engineering and benchmarking non-Gaussian entangled states that are useful for quantum-enhanced metrology.

quant-ph↗

arXiv2020

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? -- A Neural Tangent Kernel Perspective

Deep residual networks (ResNets) have demonstrated better generalization performance than deep feedforward networks (FFNets). However, the theory behind such a phenomenon is still largely unknown. This paper studies this fundamental problem in deep learning from a so-called "neural tangent kernel" perspective. Specifically, we first show that under proper conditions, as the width goes to infinity, training deep ResNets can be viewed as learning reproducing kernel functions with some kernel function. We then compare the kernel of deep ResNets with that of deep FFNets and discover that the class of functions induced by the kernel of FFNets is asymptotically not learnable, as the depth goes to infinity. In contrast, the class of functions induced by the kernel of ResNets does not exhibit such degeneracy. Our discovery partially justifies the advantages of deep ResNets over deep FFNets in generalization abilities. Numerical results are provided to support our claim.

cs.LG↗

arXiv2020

Realizing a quantum generative adversarial network using a programmable superconducting processor

Generative adversarial networks are an emerging technique with wide applications in machine learning, which have achieved dramatic success in a number of challenging tasks including image and video generation. When equipped with quantum processors, their quantum counterparts--called quantum generative adversarial networks (QGANs)--may even exhibit exponential advantages in certain machine learning applications. Here, we report an experimental implementation of a QGAN using a programmable superconducting processor, in which both the generator and the discriminator are parameterized via layers of single- and multi-qubit quantum gates. The programmed QGAN runs automatically several rounds of adversarial learning with quantum gradients to achieve a Nash equilibrium point, where the generator can replicate data samples that mimic the ones from the training set. Our implementation is promising to scale up to noisy intermediate-scale quantum devices, thus paving the way for experimental explorations of quantum advantages in practical applications with near-term quantum technologies.

quant-ph↗

arXiv2020

The possibility of the secondary object in GW190814 as a neutron star

A compact object was observed with a mass $2.50-2.67~M_\odot$ by LIGO Scientific and Virgo collaborations (LVC) in GW190814, which provides a great challenge to the investigations into the supranuclear matter. To study this object, properties of neutron star are systematically calculated within the latest density-dependent relativistic mean-field (DDRMF) parameterizations, which are determined by the ground state properties of spherical nuclei. The maximum masses of neutron star calculated by DD-MEX and DD-LZ1 sets can be around $2.55~M_\odot$ with quite stiff equations of state generated by their strong repulsive contributions from vector potentials at high densities. Their maximum speeds of sound $c_s/c$ are smaller than $\sqrt{0.8}$ at the center of neutron star and the dimensionless tidal deformabilities at $1.4~M_\odot$ are less than $800$. Furthermore, the radii of $1.4 ~M_\odot$ also satisfy the constraint from the observation of mass-radius simultaneous measurements (NICER). Therefore, we conclude that one cannot exclude the possibility of the secondary object in GW190814 as a neutron star composed of hadron matter from DDRMF models.

nucl-th↗

arXiv2020

On the Convergence of FedAvg on Non-IID Data

Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the sequences only once in a while. Despite its simplicity, it lacks theoretical guarantees under realistic settings. In this paper, we analyze the convergence of \texttt{FedAvg} on non-iid data and establish a convergence rate of $\mathcal{O}(\frac{1}{T})$ for strongly convex and smooth problems, where $T$ is the number of SGDs. Importantly, our bound demonstrates a trade-off between communication-efficiency and convergence rate. As user devices may be disconnected from the server, we relax the assumption of full device participation to partial device participation and study different averaging schemes; low device participation rate can be achieved without severely slowing down the learning. Our results indicate that heterogeneity of data slows down the convergence, which matches empirical observations. Furthermore, we provide a necessary condition for \texttt{FedAvg} on non-iid data: the learning rate $η$ must decay, even if full-gradient is used; otherwise, the solution will be $Ω(η)$ away from the optimal.

stat.ML↗