Search arXiv⌕ Search

arXiv subjects

Peng Zhao

Publications and source records attributed to Peng Zhao.

At least 145 records · Page 8Linked to original sources
arXiv2023

FedLED: Label-Free Equipment Fault Diagnosis with Vertical Federated Transfer Learning

Intelligent equipment fault diagnosis based on Federated Transfer Learning (FTL) attracts considerable attention from both academia and industry. It allows real-world industrial agents with limited samples to construct a fault diagnosis model without jeopardizing their raw data privacy. Existing approaches, however, can neither address the intense sample heterogeneity caused by different working conditions of practical agents, nor the extreme fault label scarcity, even zero, of newly deployed equipment. To address these issues, we present FedLED, the first unsupervised vertical FTL equipment fault diagnosis method, where knowledge of the unlabeled target domain is further exploited for effective unsupervised model transfer. Results of extensive experiments using data of real equipment monitoring demonstrate that FedLED obviously outperforms SOTA approaches in terms of both diagnosis accuracy (up to 4.13 times) and generality. We expect our work to inspire further study on label-free equipment fault diagnosis systematically enhanced by target domain knowledge.

cs.LG↗
arXiv2023

ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks

Network binarization exhibits great potential for deployment on resource-constrained devices due to its low computational cost. Despite the critical importance, the security of binarized neural networks (BNNs) is rarely investigated. In this paper, we present ARBiBench, a comprehensive benchmark to evaluate the robustness of BNNs against adversarial perturbations on CIFAR-10 and ImageNet. We first evaluate the robustness of seven influential BNNs on various white-box and black-box attacks. The results reveal that 1) The adversarial robustness of BNNs exhibits a completely opposite performance on the two datasets under white-box attacks. 2) BNNs consistently exhibit better adversarial robustness under black-box attacks. 3) Different BNNs exhibit certain similarities in their robustness performance. Then, we conduct experiments to analyze the adversarial robustness of BNNs based on these insights. Our research contributes to inspiring future research on enhancing the robustness of BNNs and advancing their application in real-world scenarios.

cs.CV↗
arXiv2023

Generative Model-based Feature Knowledge Distillation for Action Recognition

Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus on designing loss functions and fusing cross-modal information. This overlooks the spatial-temporal feature semantics, resulting in limited advancements in model compression. Addressing this gap, our paper introduces an innovative knowledge distillation framework, with the generative model for training a lightweight student model. In particular, the framework is organized into two steps: the initial phase is Feature Representation, wherein a generative model-based attention module is trained to represent feature semantics; Subsequently, the Generative-based Feature Distillation phase encompasses both Generative Distillation and Attention Distillation, with the objective of transferring attention-based feature semantics with the generative model. The efficacy of our approach is demonstrated through comprehensive experiments on diverse popular datasets, proving considerable enhancements in video action recognition task. Moreover, the effectiveness of our proposed framework is validated in the context of more intricate video action detection task. Our code is available at https://github.com/aaai-24/Generative-based-KD.

cs.CV↗
arXiv2023

Machine Learning-Enhanced Aircraft Landing Scheduling under Uncertainties

This paper addresses aircraft delays, emphasizing their impact on safety and financial losses. To mitigate these issues, an innovative machine learning (ML)-enhanced landing scheduling methodology is proposed, aiming to improve automation and safety. Analyzing flight arrival delay scenarios reveals strong multimodal distributions and clusters in arrival flight time durations. A multi-stage conditional ML predictor enhances separation time prediction based on flight events. ML predictions are then integrated as safety constraints in a time-constrained traveling salesman problem formulation, solved using mixed-integer linear programming (MILP). Historical flight recordings and model predictions address uncertainties between successive flights, ensuring reliability. The proposed method is validated using real-world data from the Atlanta Air Route Traffic Control Center (ARTCC ZTL). Case studies demonstrate an average 17.2% reduction in total landing time compared to the First-Come-First-Served (FCFS) rule. Unlike FCFS, the proposed methodology considers uncertainties, instilling confidence in scheduling. The study concludes with remarks and outlines future research directions.

cs.AI↗
arXiv2023

Testing the number of common factors by bootstrapped sample covariance matrix in high-dimensional factor models

This paper studies the impact of bootstrap procedure on the eigenvalue distributions of the sample covariance matrix under a high-dimensional factor structure. We provide asymptotic distributions for the top eigenvalues of bootstrapped sample covariance matrix under mild conditions. After bootstrap, the spiked eigenvalues which are driven by common factors will converge weakly to Gaussian limits after proper scaling and centralization. However, the largest non-spiked eigenvalue is mainly determined by the order statistics of the bootstrap resampling weights, and follows extreme value distribution. Based on the disparate behavior of the spiked and non-spiked eigenvalues, we propose innovative methods to test the number of common factors. Indicated by extensive numerical and empirical studies, the proposed methods perform reliably and convincingly under the existence of both weak factors and cross-sectionally correlated errors. Our technical details contribute to random matrix theory on spiked covariance model with convexly decaying density and unbounded support, or with general elliptical distributions.

math.ST↗
arXiv2023

Mitigation of quantum crosstalk in cross-resonance based qubit architectures

The Cross-resonance (CR) gate architecture that exploits fixed-frequency transmon qubits and fixed couplings is a leading candidate for quantum computing. Nonetheless, without the tunability of qubit parameters such as qubit frequencies and couplings, gate operations can be limited by the presence of quantum crosstalk arising from the always-on couplings. When increasing system sizes, this can become even more serious considering frequency collisions caused by fabrication uncertainties. Here, we introduce a CR gate-based transmon architecture with passive mitigation of both quantum crosstalk and frequency collisions. Assuming typical parameters, we show that ZZ crosstalk can be suppressed while maintaining XY couplings to support fast, high-fidelity CR gates. The architecture also allows one to go beyond the existing literature by extending the operating regions in which fast, high-fidelity CR gates are possible, thus alleviating the frequency-collision issue. To examine the practicality, we analyze the CR gate performance in multiqubit lattices and provide an intuitive model for identifying and mitigating the dominant source of error. For the state-of-the-art precision in setting frequencies, we further investigate its impact on the gates. We find that ZZ crosstalk and frequency collisions can be largely mitigated for neighboring qubits, while interactions beyond near neighbor qubits can introduce new frequency collisions. As the strength is typically at the sub-MHz level, adding weak off-resonant drives to selectively shift qubits can mitigate the collisions. This work could be useful for suppressing quantum crosstalk and improving gate fidelities in large-scale quantum processors based on fixed-frequency qubits and fixed couplings.

quant-ph↗
arXiv2023

Direct numerical simulation of Taylor-Couette flow with vertical asymmetric rough walls

Direct numerical simulations are performed to explore the effects of rotating direction of the vertical asymmetric rough wall on the transport properties of Taylor-Couette (TC) flow up to a Taylor number of $\textit{Ta} = 2.39 \times 10^7$. It is shown that compared to the smooth wall, the rough wall with vertical asymmetric strips can enhance the dimensionless torque \textit{Nu}$_ω$, and more importantly, at high \textit{Ta} clockwise rotation of the inner rough wall (the fluid is sheared by the steeper slope side of the strips) results in a significantly bigger torque enhancement as compared to the counter-clockwise rotation (the fluid is sheared by the smaller slope side of the strips) due to the larger convective contribution to the angular velocity flux, although the rotating direction has a negligible effect on the torque at low \textit{Ta}. The larger torque enhancement caused by the clockwise rotation of vertical asymmetric rough wall at high \textit{Ta} is then explained by the stronger coupling between the rough wall and the bulk due to the larger biased azimuthal velocity towards the rough wall at the mid-gap of TC system, the increased intensity of turbulence manifesting by larger Reynolds stress and thinner boundary layer, and the more significant contribution of the pressure force on the surface of rough wall to the torque.

physics.flu-dyn↗
arXiv2023

Mitigating crosstalk and residual coupling errors in superconducting quantum processors using many-body localization

Addressing the paramount need for precise calibration in superconducting quantum qubits, especially in frequency control, this study introduces a novel calibration scheme harnessing the principles of Many-Body Localization (MBL). While existing strategies, such as Google's snake algorithm, have targeted optimization of qubit frequency parameters, our MBL-based methodology emerges as a stalwart against noise, notably crosstalk and residual coupling errors, thereby significantly enhancing quantum processor fidelity and stability without necessitating extensive optimization computation. Not only does this approach provide a marked improvement in performance, particularly where specific residue couplings are present, but it also presents a more resource-efficient and cost-effective calibration process. The research delineated herein affords fresh insights into advanced calibration strategies and propels forward the domain of superconducting quantum computation by offering a robust framework for future explorations in minimizing error and optimizing qubit performance.

quant-ph↗
arXiv2023

Task allocation planning based on HTN for national economic mobilization

In order to cope with the task allocation in national economic mobilization, a task allocation planning method based on Hierarchical Task Network (HTN) for national economic mobilization is proposed. An HTN planning algorithm is designed to solve and optimize task allocation, and a method is explored to deal with the resource shortage. Finally, based on a real task allocation case in national economic mobilization, an experimental study verifies the effectiveness of the proposed method.

cs.CY↗
arXiv2023

Probabilistic contingent planning based on HTN for high-quality plans

Deterministic planning assumes that the planning evolves along a fully predictable path, and therefore it loses the practical value in most real projections. A more realistic view is that planning ought to take into consideration partial observability beforehand and aim for a more flexible and robust solution. What is more significant, it is inevitable that the quality of plan varies dramatically in the partially observable environment. In this paper we propose a probabilistic contingent Hierarchical Task Network (HTN) planner, named High-Quality Contingent Planner (HQCP), to generate high-quality plans in the partially observable environment. The formalisms in HTN planning are extended into partial observability and are evaluated regarding the cost. Next, we explore a novel heuristic for high-quality plans and develop the integrated planning algorithm. Finally, an empirical study verifies the effectiveness and efficiency of the planner both in probabilistic contingent planning and for obtaining high-quality plans.

cs.AI↗
arXiv2023

Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled instances are supervised by classifying labeled bags. The MIL-based methods are relatively well studied with cogent performance achieved on classification but not on localization. Generally, they locate temporal regions by the video-level classification but overlook the temporal variations of feature semantics. To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics. Specifically, our model entails two components, the first is an unsupervised change-points detection module that detects change-points by learning the latent representations of video features in a temporal hierarchy based on their rates of change, and the second is an attention-based classification model that selects the change-points of the foreground as the boundaries. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNet-v1.3. The experiments show that our method outperforms current state-of-the-art methods, and even achieves comparable performance with fully-supervised methods.

cs.CV↗
arXiv2023

Frequentist Model Averaging for Global Fréchet Regression

To consider model uncertainty in global Fréchet regression and improve density response prediction, we propose a frequentist model averaging method. The weights are chosen by minimizing a cross-validation criterion based on Wasserstein distance. In the cases where all candidate models are misspecified, we prove that the corresponding model averaging estimator has asymptotic optimality, achieving the lowest possible Wasserstein distance. When there are correctly specified candidate models, we prove that our method asymptotically assigns all weights to the correctly specified models. Numerical results of extensive simulations and a real data analysis on intracerebral hemorrhage data strongly favour our method.

stat.ME↗
arXiv2023

Non-stationary Online Learning with Memory and Non-stochastic Control

We study the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to depend on past decisions and thus captures temporal effects of learning problems. In this paper, we introduce dynamic policy regret as the performance measure to design algorithms robust to non-stationary environments, which competes algorithms' decisions with a sequence of changing comparators. We propose a novel algorithm for OCO with memory that provably enjoys an optimal dynamic policy regret in terms of time horizon, non-stationarity measure, and memory length. The key technical challenge is how to control the switching cost, the cumulative movements of player's decisions, which is neatly addressed by a novel switching-cost-aware online ensemble approach equipped with a new meta-base decomposition of dynamic policy regret and a careful design of meta-learner and base-learner that explicitly regularizes the switching cost. The results are further applied to tackle non-stationarity in online non-stochastic control (Agarwal et al., 2019), i.e., controlling a linear dynamical system with adversarial disturbance and convex cost functions. We derive a novel gradient-based controller with dynamic policy regret guarantees, which is the first controller provably competitive to a sequence of changing policies for online non-stochastic control.

cs.LG↗
arXiv2023

Improving the Transferability of Adversarial Examples via Direction Tuning

In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although considerable efforts have been developed on improving the transferability of adversarial examples generated by transfer-based adversarial attacks, our investigation found that, the big deviation between the actual and steepest update directions of the current transfer-based adversarial attacks is caused by the large update step length, resulting in the generated adversarial examples can not converge well. However, directly reducing the update step length will lead to serious update oscillation so that the generated adversarial examples also can not achieve great transferability to the victim models. To address these issues, a novel transfer-based attack, namely direction tuning attack, is proposed to not only decrease the update deviation in the large step length, but also mitigate the update oscillation in the small sampling step length, thereby making the generated adversarial examples converge well to achieve great transferability on victim models. In addition, a network pruning method is proposed to smooth the decision boundary, thereby further decreasing the update oscillation and enhancing the transferability of the generated adversarial examples. The experiment results on ImageNet demonstrate that the average attack success rate (ASR) of the adversarial examples generated by our method can be improved from 87.9\% to 94.5\% on five victim models without defenses, and from 69.1\% to 76.2\% on eight advanced defense methods, in comparison with that of latest gradient-based attacks.

cs.CV↗
arXiv2023

Notes on Worldsheet-Like Variables for Cluster Configuration Spaces

We continue the exploration of various appearances of cluster algebras in scattering amplitudes and related topics in physics. The cluster configuration spaces generalize the familiar moduli space ${\mathcal M}_{0,n}$ to finite-type cluster algebras. We study worldsheet-like variables, which for classical types have also appeared in the study of the symbol alphabet of Feynman integrals. We provide a systematic derivation of these variables from $Y$-systems, which allows us to express the dihedral coordinates in terms of them and to write the corresponding cluster string integrals in compact forms. We mainly focus on the $D_n$ type and show how to reach the boundaries of the configuration space, and write the saddle-point equations in terms of these variables. Moreover, these variables make it easier to study various topological properties of the space using a finite-field method. We propose conjectures about quasi-polynomial point count, dimensions of cohomology, and the number of saddle points for the $D_n$ space up to $n=10$, which greatly extend earlier results.

hep-th↗
arXiv2023

Revisiting Weighted Strategy for Non-stationary Parametric Bandits

Non-stationary parametric bandits have attracted much attention recently. There are three principled ways to deal with non-stationarity, including sliding-window, weighted, and restart strategies. As many non-stationary environments exhibit gradual drifting patterns, the weighted strategy is commonly adopted in real-world applications. However, previous theoretical studies show that its analysis is more involved and the algorithms are either computationally less efficient or statistically suboptimal. This paper revisits the weighted strategy for non-stationary parametric bandits. In linear bandits (LB), we discover that this undesirable feature is due to an inadequate regret analysis, which results in an overly complex algorithm design. We propose a refined analysis framework, which simplifies the derivation and importantly produces a simpler weight-based algorithm that is as efficient as window/restart-based algorithms while retaining the same regret as previous studies. Furthermore, our new framework can be used to improve regret bounds of other parametric bandits, including Generalized Linear Bandits (GLB) and Self-Concordant Bandits (SCB). For example, we develop a simple weighted GLB algorithm with an $\widetilde{O}(k_μ^{\frac{5}{4}} c_μ^{-\frac{3}{4}} d^{\frac{3}{4}} P_T^{\frac{1}{4}}T^{\frac{3}{4}})$ regret, improving the $\widetilde{O}(k_μ^{2} c_μ^{-1}d^{\frac{9}{10}} P_T^{\frac{1}{5}}T^{\frac{4}{5}})$ bound in prior work, where $k_μ$ and $c_μ$ characterize the reward model's nonlinearity, $P_T$ measures the non-stationarity, $d$ and $T$ denote the dimension and time horizon.

cs.LG↗
arXiv2023

Spatial Clustering Regression of Count Value Data via Bayesian Mixture of Finite Mixtures

Investigating relationships between response variables and covariates in areas such as environmental science, geoscience, and public health is an important endeavor. Based on a Bayesian mixture of finite mixtures model, we present a novel spatially clustered coefficients regression model for count value data. The proposed method detects the spatial homogeneity of the Poisson regression coefficients. A Markov random field constrained mixture of finite mixtures prior provides a regularized estimator of the number of clusters of regression coefficients with geographical neighborhood information. As a by-product, we also provide the theoretical properties of our proposed method when the Markov random field is exchangeable. An efficient Markov chain Monte Carlo algorithm is developed by using the multivariate log gamma distribution as a base distribution. Simulation studies are carried out to examine the empirical performance of the proposed method. Additionally, we analyze Georgia's premature death data as an illustration of the effectiveness of our approach. The supplementary materials are provided on GitHub at \url{https://github.com/pengzhaostat/MLG_MFM}.

stat.ME↗
arXiv2023

Baseband control of superconducting qubits with shared microwave drives

Accurate control of qubits is the central requirement for building functional quantum processors. For the current superconducting quantum processor, high-fidelity control of qubits is mainly based on independently calibrated microwave pulses, which could differ from each other in frequencies, amplitudes, and phases. With this control strategy, the needed physical source could be challenging, especially when scaling up to large-scale quantum processors is considered. Inspired by Kane's proposal for spin-based quantum computing, here, we explore theoretically the possibility of baseband flux control of superconducting qubits with only shared and always-on microwave drives. In our strategy, qubits are by default far detuned from the drive during system idle periods, qubit readout and baseband flux-controlled two-qubit gates can thus be realized with minimal impacts from the always-on drive. By contrast, during working periods, qubits are tuned on resonance with the drive and single-qubit gates can be realized. Therefore, universal qubit control can be achieved with only baseband flux pulses and always-on shared microwave drives. We apply this strategy to the qubit architecture where tunable qubits are coupled via a tunable coupler, and the analysis shows that high-fidelity qubit control is possible. Besides, the baseband control strategy needs fewer physical resources, such as control electronics and cooling power in cryogenic systems, than that of microwave control. More importantly, the flexibility of baseband flux control could be employed for addressing the non-uniformity issue of superconducting qubits, potentially allowing the realization of multiplexing and cross-bar technologies and thus controlling large numbers of qubits with fewer control lines. We thus expect that baseband control with shared microwave drives can help build large-scale superconducting quantum processors.

quant-ph↗