arXiv subjects

Tao Zhang

Publications and source records attributed to Tao Zhang.

At least 505 records · Page 28Linked to original sources

arXiv2022

STBPU: A Reasonably Secure Branch Prediction Unit

Modern processors have suffered a deluge of threats exploiting branch instruction collisions inside the branch prediction unit (BPU), from eavesdropping on secret-related branch operations to triggering malicious speculative executions. Protecting branch predictors tends to be challenging from both security and performance perspectives. For example, partitioning or flushing BPU can stop certain collision-based exploits but only to a limited extent. Meanwhile, such mitigations negatively affect branch prediction accuracy and further CPU performance. This paper proposes Secret Token Branch Prediction Unit (STBPU), a secure BPU design to defend against collision-based transient execution attacks and BPU side channels while incurring minimal performance overhead. STBPU resolves the challenges above by customizing data representation inside BPU for each software entity requiring isolation. In addition, to prevent an attacker from using brute force techniques to trigger malicious branch instruction collisions, STBPU actively monitors the prediction-related events and preemptively changes BPU data representation.

cs.CR↗

arXiv2022

Self-Aware Personalized Federated Learning

In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned. Inspired by Bayesian hierarchical models, we develop a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients' training. Such a balance is derived from the inter-client and intra-client uncertainty quantification. A larger inter-client variation implies more personalization is needed. Correspondingly, our method uses uncertainty-driven local training steps and aggregation rule instead of conventional local fine-tuning and sample size-based aggregation. With experimental studies on synthetic data, Amazon Alexa audio data, and public datasets such as MNIST, FEMNIST, CIFAR10, and Sent140, we show that our proposed method can achieve significantly improved personalization performance compared with the existing counterparts.

cs.LG↗

arXiv2022

A Search for the Cosmic Ray Boosted Sub-GeV Dark Matter at the PandaX-II Experiment

We report a novel search for the cosmic ray boosted dark matter using the 100~tonne$\cdot$day full data set of the PandaX-II detector located at the China Jinping Underground Laboratory. With the extra energy gained from the cosmic rays, sub-GeV dark matter particles can produce visible recoil signals in the detector. The diurnal modulations in rate and energy spectrum are utilized to further enhance the signal sensitivity. Our result excludes the dark matter-nucleon elastic scattering cross section between 10$^{-31}$cm$^{2}$ and 10$^{-28}$cm$^{2}$ for a dark matter masses from 0.1 MeV/$c^2$ to 0.1 GeV/$c^2$, with a large parameter space previously unexplored by experimental collaborations.

hep-ex↗

arXiv2022

Alternating direction method of multipliers for convex programming: a lift-and-permute scheme

A lift-and-permute scheme of alternating direction method of multipliers (ADMM) is proposed for linearly constrained convex programming. It contains not only the newly developed balanced augmented Lagrangian method and its dual-primal variation, but also the proximal ADMM and Douglas-Rachford splitting algorithm. It helps to propose accelerated algorithms with worst-case $O(1/k^2)$ convergence rates in the case that the objective function to be minimized is strongly convex.

math.OC↗

arXiv2022

SuperMVS: Non-Uniform Cost Volume For High-Resolution Multi-View Stereo

Different from most state-of-the-art~(SOTA) algorithms that use static and uniform sampling methods with a lot of hypothesis planes to get fine depth sampling. In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume. We present the SuperMVS network to implement Multi-View Stereo with Non-Uniform Cost Volume. SuperMVS is a coarse-to-fine framework with four cascade stages. It can output higher resolution and accurate depth map. Our SuperMVS achieves the SOTA results with low memory, low runtime, and fewer planes on the DTU datasets and Tanks \& Temples dataset.

cs.CV↗

arXiv2022

Leveraging Search History for Improving Person-Job Fit

As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates. However, existing studies mainly focus on the recommendation scenario, while neglecting another important channel for linking positions with job seekers, i.e. search. Intuitively, search history contains rich user behavior in job seeking, reflecting important evidence for job intention of users. In this paper, we present a novel Search History enhanced Person-Job Fit model, named as SHPJF. To utilize both text content from jobs/resumes and search histories from users, we propose two components with different purposes. For text matching component, we design a BERT-based text encoder for capturing the semantic interaction between resumes and job descriptions. For intention modeling component, we design two kinds of intention modeling approaches based on the Transformer architecture, either based on the click sequence or query text sequence. To capture underlying job intentions, we further propose an intention clustering technique to identify and summarize the major intentions from search logs. Extensive experiments on a large real-world recruitment dataset have demonstrated the effectiveness of our approach.

cs.IR↗

arXiv2022

kDecay: Just adding k-decay items on Learning-Rate Schedule to improve Neural Networks

Recent work has shown that optimizing the Learning Rate (LR) schedule can be a very accurate and efficient way to train deep neural networks. We observe that the rate of change (ROC) of LR has correlation with the training process, but how to use this relationship to control the training to achieve the purpose of improving accuracy? We propose a new method, k-decay, just add an extra item to the commonly used and easy LR schedule(exp, cosine and polynomial), is effectively improves the performance of these schedule, also better than the state-of-the-art algorithms of LR shcedule such as SGDR, CLR and AutoLRS. In the k-decay, by adjusting the hyper-parameter $k$, to generate different LR schedule, when k increases, the performance is improved. We evaluate the k-decay method on CIFAR And ImageNet datasets with different neural networks (ResNet, Wide ResNet). Our experiments show that this method can improve on most of them. The accuracy has been improved by 1.08\% on the CIFAR-10 dataset and by 2.07 \% on the CIFAR-100 dataset. On the ImageNet, accuracy is improved by 1.25\%. Our method is not only a general method to be applied other LR Shcedule, but also has no additional computational cost.

cs.LG↗

arXiv2022

Braided Hom-Lie bialgebras

We introduce the new concept of braided Hom-Lie bialgebras which is a generalization of Sommerhäuser-Majid's braided Lie bialgebras and Yau's Hom-Lie bialgebras. Using this concept we give the unified product construction for Hom-Lie bialgebras which can be seen as a Hom-Lie version of Bespalov-Drabant's cocycle cross product bialgebras. Some special cases of unified products such as crossed product and matched pair of braided Hom-Lie bialgebras are investigated. As an application, we solve the Agore-Militaru extending problem for Hom-Lie bialgebras by using some non-abelian cohomology theory. Furthermore, one dimensional flag extending structures for Hom-Lie bialgebras are also investigated.

math.QA↗

arXiv2022

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of hand-crafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512*512 images on an NVIDIA A6000 GPU. Code will be released at https://github.com/zhang-tao-whu/e2ec.

cs.CV↗

arXiv2022

Unified products for Zinbiel 2-algebras

The extending structures problem for Zinbiel 2-algebras is studied. We introduce the concept of unified products for Zinbiel 2-algebras. Some special cases of unified products such as crossed product and matched pair of Zinbiel 2-algebras are investigated. It is proved that the extending problem for Zinbiel 2-algebras can be classified by some non-abelian cohomology theory.

math.RA↗

arXiv2022

RRL:Regional Rotation Layer in Convolutional Neural Networks

Convolutional Neural Networks (CNNs) perform very well in image classification and object detection in recent years, but even the most advanced models have limited rotation invariance. Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features. These methods either increase the workload of training or increase the number of model parameters. To address this problem, this paper proposes a module that can be inserted into the existing networks, and directly incorporates the rotation invariance into the feature extraction layers of the CNNs. This module does not have learnable parameters and will not increase the complexity of the model. At the same time, only by training the upright data, it can perform well on the rotated testing set. These advantages will be suitable for fields such as biomedicine and astronomy where it is difficult to obtain upright samples or the target has no directionality. Evaluate our module with LeNet-5, ResNet-18 and tiny-yolov3, we get impressive results.

cs.CV↗

arXiv2022

End-to-end Alexa Device Arbitration

We introduce a variant of the speaker localization problem, which we call device arbitration. In the device arbitration problem, a user utters a keyword that is detected by multiple distributed microphone arrays (smart home devices), and we want to determine which device was closest to the user. Rather than solving the full localization problem, we propose an end-to-end machine learning system. This system learns a feature embedding that is computed independently on each device. The embeddings from each device are then aggregated together to produce the final arbitration decision. We use a large-scale room simulation to generate training and evaluation data, and compare our system against a signal processing baseline.

eess.AS↗

arXiv2022

Characterization of Pedestal Burst Instabilities during I-mode to H-mode Transition in the EAST Tokamak

Quasi-periodic Pedestal Burst Instabilities (PBIs), featuring alternative turbulence suppression and bursts, have been clearly identified by various edge diagnostics during I-mode to H-mode transition in the EAST Tokamak. The radial distribution of the phase perturbation caused by PBI shows that PBI is localized in the pedestal. Prior to each PBI, a significant increase of density gradient close to the pedestal top can be clearly distinguished, then the turbulence burst is generated, accompanied by the relaxation of the density profile, and then induces an outward particle flux. The relative density perturbation caused by PBIs is about $6 \sim 8\%$. Statistic analyses show that the pedestal normalized density gradient triggering the first PBI has a threshold value, mostly in the range of $22 \sim 24$, suggesting that a PBI triggering instability could be driven by the density gradient. And the pedestal normalized density gradient triggering the last PBI is about $30 \sim 40$ and seems to increase with the loss power and the chord-averaged density. In addition, the frequency of PBI is likely to be inversely proportional to the chord-averaged density and the loss power. These results suggest that PBIs and the density gradient prompt increase prior to PBIs can be considered as the precursor for controlling I-H transition.

physics.plasm-ph↗

arXiv2022

Federated Learning Challenges and Opportunities: An Outlook

Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs. Although many methods and applications have been developed for FL, several critical challenges for practical FL systems remain unaddressed. This paper provides an outlook on FL development, categorized into five emerging directions of FL, namely algorithm foundation, personalization, hardware and security constraints, lifelong learning, and nonstandard data. Our unique perspectives are backed by practical observations from large-scale federated systems for edge devices.

cs.LG↗

arXiv2022

End-to-End Quality-of-Service Assurance with Autonomous Systems: 5G/6G Case Study

Providing differentiated services to meet the unique requirements of different use cases is a major goal of the fifth generation (5G) telecommunication networks and will be even more critical for future 6G systems. Fulfilling this goal requires the ability to assure quality of service (QoS) end to end (E2E), which remains a challenge. A key factor that makes E2E QoS assurance difficult in a telecommunication system is that access networks (ANs) and core networks (CNs) manage their resources autonomously. So far, few results have been available that can ensure E2E QoS over autonomously managed ANs and CNs. Existing techniques rely predominately on each subsystem to meet static local QoS budgets with no recourse in case any subsystem fails to meet its local budgets and, hence will have difficulty delivering E2E assurance. Moreover, most existing distributed optimization techniques that can be applied to assure E2E QoS over autonomous subsystems require the subsystems to exchange sensitive information such as their local decision variables. This paper presents a novel framework and a distributed algorithm that can enable ANs and CNs to autonomously "cooperate" with each other to dynamically negotiate their local QoS budgets and to collectively meet E2E QoS goals by sharing only their estimates of the global constraint functions, without disclosing their local decision variables. We prove that this new distributed algorithm converges to an optimal solution almost surely, and also present numerical results to demonstrate that the convergence occurs quickly even with measurement noise.

eess.SY↗

arXiv2022

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks. However, the effect of the standard PGD attack can be easily weakened by rescaling the logits, while the original decision of every input will not be changed. To mitigate this issue, in this paper, we propose Scale-Invariant Adversarial Attack (SI-PGD), which utilizes the angle between the features in the penultimate layer and the weights in the softmax layer to guide the generation of adversaries. The cosine angle matrix is used to learn angularly discriminative representation and will not be changed with the rescaling of logits, thus making SI-PGD attack to be stable and effective. We evaluate our attack against multiple defenses and show improved performance when compared with existing attacks. Further, we propose Scale-Invariant (SI) adversarial defense mechanism based on the cosine angle matrix, which can be embedded into the popular adversarial defenses. The experimental results show the defense method with our SI mechanism achieves state-of-the-art performance among multi-step and single-step defenses.

cs.CV↗

arXiv2022

Bayesian Promised Persuasion: Dynamic Forward-Looking Multiagent Delegation with Informational Burning

This work studies a dynamic mechanism design problem in which a principal delegates decision makings to a group of privately-informed agents without the monetary transfer or burning. We consider that the principal privately possesses complete knowledge about the state transitions and study how she can use her private observation to support the incentive compatibility of the delegation via informational burning, a process we refer to as the looking-forward persuasion. The delegation mechanism is formulated in which the agents form belief hierarchies due to the persuasion and play a dynamic Bayesian game. We propose a novel randomized mechanism, known as Bayesian promised delegation (BPD), in which the periodic incentive compatibility is guaranteed by persuasions and promises of future delegations. We show that the BPD can achieve the same optimal social welfare as the original mechanism in stationary Markov perfect Bayesian equilibria. A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.

cs.GT↗

arXiv2022

Multi-layer VI-GNSS Global Positioning Framework with Numerical Solution aided MAP Initialization

Motivated by the goal of achieving long-term drift-free camera pose estimation in complex scenarios, we propose a global positioning framework fusing visual, inertial and Global Navigation Satellite System (GNSS) measurements in multiple layers. Different from previous loosely- and tightly- coupled methods, the proposed multi-layer fusion allows us to delicately correct the drift of visual odometry and keep reliable positioning while GNSS degrades. In particular, local motion estimation is conducted in the inner-layer, solving the problem of scale drift and inaccurate bias estimation in visual odometry by fusing the velocity of GNSS, pre-integration of Inertial Measurement Unit (IMU) and camera measurement in a tightly-coupled way. The global localization is achieved in the outer-layer, where the local motion is further fused with GNSS position and course in a long-term period in a loosely-coupled way. Furthermore, a dedicated initialization method is proposed to guarantee fast and accurate estimation for all state variables and parameters. We give exhaustive tests of the proposed framework on indoor and outdoor public datasets. The mean localization error is reduced up to 63%, with a promotion of 69% in initialization accuracy compared with state-of-the-art works. We have applied the algorithm to Augmented Reality (AR) navigation, crowd sourcing high-precision map update and other large-scale applications.

cs.RO↗