ترغب بنشر مسار تعليمي؟ اضغط هنا

352 - Jin Li , Ye Luo , Xiaowei Zhang 2021
In this paper, we study endogeneity problems in algorithmic decision-making where data and actions are interdependent. When there are endogenous covariates in a contextual multi-armed bandit model, a novel bias (self-fulfilling bias) arises because t he endogeneity of the covariates spills over to the actions. We propose a class of algorithms to correct for the bias by incorporating instrumental variables into leading online learning algorithms. These algorithms also attain regret levels that match the best known lower bound for the cases without endogeneity. To establish the theoretical properties, we develop a general technique that untangles the interdependence between data and actions.
114 - Jin Li , Ye Luo , Xiaowei Zhang 2021
In the standard data analysis framework, data is first collected (once for all), and then data analysis is carried out. With the advancement of digital technology, decisionmakers constantly analyze past data and generate new data through the decision s they make. In this paper, we model this as a Markov decision process and show that the dynamic interaction between data generation and data analysis leads to a new type of bias -- reinforcement bias -- that exacerbates the endogeneity problem in standard data analysis. We propose a class of instrument variable (IV)-based reinforcement learning (RL) algorithms to correct for the bias and establish their asymptotic properties by incorporating them into a two-timescale stochastic approximation framework. A key contribution of the paper is the development of new techniques that allow for the analysis of the algorithms in general settings where noises feature time-dependency. We use the techniques to derive sharper results on finite-time trajectory stability bounds: with a polynomial rate, the entire future trajectory of the iterates from the algorithm fall within a ball that is centered at the true parameter and is shrinking at a (different) polynomial rate. We also use the technique to provide formulas for inferences that are rarely done for RL algorithms. These formulas highlight how the strength of the IV and the degree of the noises time dependency affect the inference.
62 - Shiqing Fan , Ye Luo 2021
Low-quality face image restoration is a popular research direction in todays computer vision field. It can be used as a pre-work for tasks such as face detection and face recognition. At present, there is a lot of work to solve the problem of low-qua lity faces under various environmental conditions. This paper mainly focuses on the restoration of motion-blurred faces. In increasingly abundant mobile scenes, the fast recovery of motion-blurred faces can bring highly effective speed improvements in tasks such as face matching. In order to achieve this goal, a deblurring method for motion-blurred facial image signals based on generative adversarial networks(GANs) is proposed. It uses an end-to-end method to train a sharp image generator, i.e., a processor for motion-blurred facial images. This paper introduce the processing progress of motion-blurred images, the development and changes of GANs and some basic concepts. After that, it give the details of network structure and training optimization design of the image processor. Then we conducted a motion blur image generation experiment on some general facial data set, and used the pairs of blurred and sharp face image data to perform the training and testing experiments of the processor GAN, and gave some visual displays. Finally, MTCNN is used to detect the faces of the image generated by the deblurring processor, and compare it with the result of the blurred image. From the results, the processing effect of the deblurring processor on the motion-blurred picture has a significant improvement both in terms of intuition and evaluation indicators of face detection.
57 - Shiqing Fan , Liu Liying , Ye Luo 2021
Convolutional neural networks (CNNs) have been used in many machine learning fields. In practical applications, the computational cost of convolutional neural networks is often high with the deepening of the network and the growth of data volume, mos tly due to a large amount of multiplication operations of floating-point numbers in convolution operations. To reduce the amount of multiplications, we propose a new type of CNNs called Tropical Convolutional Neural Networks (TCNNs) which are built on tropical convolutions in which the multiplications and additions in conventional convolutional layers are replaced by additions and min/max operations respectively. In addition, since tropical convolution operators are essentially nonlinear operators, we expect TCNNs to have higher nonlinear fitting ability than conventional CNNs. In the experiments, we test and analyze several different architectures of TCNNs for image classification tasks in comparison with similar-sized conventional CNNs. The results show that TCNN can achieve higher expressive power than ordinary convolutional layers on the MNIST and CIFAR10 image data set. In different noise environments, there are wins and losses in the robustness of TCNN and ordinary CNNs.
391 - Ye Luo , Shiqing Fan 2021
We present a new model of neural networks called Min-Max-Plus Neural Networks (MMP-NNs) based on operations in tropical arithmetic. In general, an MMP-NN is composed of three types of alternately stacked layers, namely linear layers, min-plus layers and max-plus layers. Specifically, the latter two types of layers constitute the nonlinear part of the network which is trainable and more sophisticated compared to the nonlinear part of conventional neural networks. In addition, we show that with higher capability of nonlinearity expression, MMP-NNs are universal approximators of continuous functions, even when the number of multiplication operations is tremendously reduced (possibly to none in certain extreme cases). Furthermore, we formulate the backpropagation algorithm in the training process of MMP-NNs and introduce an algorithm of normalization to improve the rate of convergence in training.
Automatic segmentation of the prostate cancer from the multi-modal magnetic resonance images is of critical importance for the initial staging and prognosis of patients. However, how to use the multi-modal image features more efficiently is still a c hallenging problem in the field of medical image segmentation. In this paper, we develop a cross-modal self-attention distillation network by fully exploiting the encoded information of the intermediate layers from different modalities, and the extracted attention maps of different modalities enable the model to transfer the significant spatial information with more details. Moreover, a novel spatial correlated feature fusion module is further employed for learning more complementary correlation and non-linear information of different modality images. We evaluate our model in five-fold cross-validation on 358 MRI with biopsy confirmed. Extensive experiment results demonstrate that our proposed network achieves state-of-the-art performance.
Diffusion Monte Carlo (DMC) calculations were performed for an accurate description of the nature of the O$_2$ adsorption on a single layer graphene. We investigated the stable orientation of O$_2$ at a specific adsorption site as well as its equilib rium adsorption energy. At equilibrium adsorption distances, an O$_2$ molecule was found to prefer a horizontal orientation, where the O-O bond is parallel to the graphene surface, to the vertical orientation. However, the vertical orientation is favored at the O$_2$-graphene distances shorter than the equilibrium distance, which could be understood by the steric repulsion between O and C atoms. Contrary to previous DFT calculations, our DMC calculations show that the midpoint of a C-C bond (a bridge site) is energetically preferred for the O$_2$ adsorption to a center of a hexagonal ring (a hollow site). The lowest DMC adsorption energy was found at an intermediate point between a hollow and a bridge site, where the O$_2$ adsorption energy was estimated to be -0.142(4) eV that was in very good agreement with the recently-reported experimental value. Finally, we have found that O$_2$ is very diffusive on the surface of graphene with the diffusion barrier along a bridge-hollow-bridge path being as small as ~ 11 meV.
Zirconia (zirconium dioxide) and hafnia (hafnium dioxide) are binary oxides used in a range of applications. Because zirconium and hafnium are chemically equivalent, they have three similar polymorphs, and it is important to understand the properties and energetics of these polymorphs. However, while density functional theory calculations can get the correct energetic ordering, the energy differences between polymorphs depend very much on the specific density functional theory approach, as do other quantities such as lattice constants and bulk modulus. We have used highly accurate quantum Monte Carlo simulations to model the three zirconia and hafnia polymorphs. We compare our results for structural parameters, bulk modulus, and cohesive energy with results obtained from density functional theory calculations. We also discuss comparisons of our results with existing experimental data, in particular for structural parameters where extrapolation to zero temperature can be attempted. We hope our results of structural parameters as well as for cohesive energy and bulk modulus can serve as benchmarks for density-functional theory based calculations and as a guidance for future experiments.
56 - Linqing Liu , Yao Lu , Ye Luo 2016
Spammer detection on social network is a challenging problem. The rigid anti-spam rules have resulted in emergence of smart spammers. They resemble legitimate users who are difficult to identify. In this paper, we present a novel spammer classificati on approach based on Latent Dirichlet Allocation(LDA), a topic model. Our approach extracts both the local and the global information of topic distribution patterns, which capture the essence of spamming. Tested on one benchmark dataset and one self-collected dataset, our proposed method outperforms other state-of-the-art methods in terms of averaged F1-score.
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا