Yang Feng

Yang Feng
Are you Yang Feng?

Claim your profile, edit publications, add additional information:

Contact Details

Yang Feng

Pubs By Year

Pub Categories

Statistics - Methodology (17)
Statistics - Theory (11)
Mathematics - Statistics (11)
Quantum Physics (10)
Statistics - Machine Learning (10)
Physics - Mesoscopic Systems and Quantum Hall Effect (8)
Statistics - Applications (5)
Physics - Materials Science (4)
Statistics - Computation (3)
Computer Science - Computation and Language (3)
Computer Science - Learning (2)
Computer Science - Computer Vision and Pattern Recognition (2)
Computer Science - Artificial Intelligence (1)
Computer Science - Neural and Evolutionary Computing (1)
Computer Science - Sound (1)
Computer Science - Computers and Society (1)

Publications Authored By Yang Feng

It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn abstract rules, while poem generation is a highly creative process that involves not only rules but also innovations for which pure statistical models are not appropriate in principle. This work proposes a memory-augmented neural model for Chinese poem generation, where the neural model and the augmented memory work together to balance the requirements of linguistic accordance and aesthetic innovation, leading to innovative generations that are still rule-compliant. Read More

Speeding up adiabatic method has attracted much attention with the wide applications in quantum information processing. In this paper, two kinds of methods, Lewis-Riesenfeld invariant-based inverse engineering and transitionless quantum driving are applied to implement speeding up adiabatic state conversion in optomechanical system. The perfect population transfer can be achieved within a short time. Read More

In this paper, we propose a web-centered framework to infer voter preferences for the 2016 U.S. presidential primaries. Read More

Gender is playing an important role in the 2016 U.S. presidential election, especially with Hillary Clinton becoming the first female presidential nominee and Donald Trump being frequently accused of sexism. Read More

Community detection is one of the fundamental problems in the study of network data. Most existing community detection approaches only consider edge information as inputs, and the output could be suboptimal when nodal information is available. In such cases, it is desirable to leverage nodal information for the improvement of community detection accuracy. Read More

We study to what extend Chinese, Japanese and Korean faces can be classified and which facial attributes offer the most important cues. First, we propose a novel way of obtaining large numbers of facial images with nationality labels. Then we train state-of-the-art neural networks with these labeled images. Read More

Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the remarkable performance remain unclear in many applications, e.g. Read More

This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the output of one task is fed as the input of the other, leading to a collaborative learning framework that can improve both language and speaker recognition by borrowing information from each other. Our experiments demonstrated that the multi-task model outperforms the task-specific models on both tasks. Read More

In many binary classification applications such as disease diagnosis and spam detection, practitioners often face great needs to control type I errors (e.g., chances of missing a malignant tumor) under a desired threshold. Read More

We propose a method to achieve strong coupling between a spin ensemble and a large Josephson junctions (LJJ). Then, the strong coupling between two spin ensembles can be induced by a LJJ. A non-adiabatic holonomic single-qubit quantum gates is realized. Read More

In this paper, we study the likelihood of Bernie Sanders supporters voting for Donald Trump instead of Hillary Clinton. Building from a unique time-series dataset of the three candidates' Twitter followers, which we make public here, we first study the proportion of Sanders followers who simultaneously follow Trump (but not Clinton) and how this evolves over time. Then we train a convolutional neural network to classify the gender of Sanders followers, and study whether men are more likely to jump ship for Trump than women. Read More

The quantized version of the anomalous Hall effect has been predicted to occur in magnetic topological insulators, but the experimental realization has been challenging. Here, we report the observation of the quantum anomalous Hall (QAH) effect in thin films of Cr-doped (Bi,Sb)2Te3, a magnetic topological insulator. At zero magnetic field, the gate-tuned anomalous Hall resistance reaches the predicted quantized value of h/e^2,accompanied by a considerable drop of the longitudinal resistance. Read More

In this paper, we propose a data-driven method to measure the impact of the 'woman card' exchange between Hillary Clinton and Donald Trump. Building from a unique dataset of the two candidates' Twitter followers, we first examine the transition dynamics of the two candidates' Twitter followers one week before the exchange and one week after. Then we train a convolutional neural network to classify the gender of the followers and unfollowers, and study how women in particular are reacting to the 'woman card' exchange. Read More

In this paper, we focus on studying the appearing time of different kinds of cars on the road. This information will enable us to infer the life style of the car owners. The results can further be used to guide marketing towards car owners. Read More

In high-dimensional data settings where $p\gg n$, many penalized regularization approaches were studied for simultaneous variable selection and estimation. However, with the existence of covariates with weak effect, many existing variable selection methods, including Lasso and its generations, cannot distinguish covariates with weak and no contribution. Thus, prediction based on a subset model of selected covariates only can be inefficient. Read More

Nowadays, quantum router is playing a key role in quantum communication and quantum network- s. Here we propose a tunable single-photon routing scheme, based on quantum interference, which uses two distant artificial atoms coupling to two transmission lines. Depending on the distance between the two atoms, the collective effect will lead to destructive or constructive interference between the scattered photons. Read More

Most existing binary classification methods target on the optimization of the overall classification risk and may fail to serve some real-world applications such as cancer diagnosis, where users are more concerned with the risk of misclassifying one specific class than the other. Neyman-Pearson (NP) paradigm was introduced in this context as a novel statistical framework for handling asymmetric type I/II error priorities. It seeks classifiers with a minimal type II error and a constrained type I error under a user specified level. Read More

Quantile regression is often used when a comprehensive relationship between a response variable and one or more explanatory variables is desired. The traditional frequentists' approach to quantile regression has been well developed around asymptotic theories and efficient algorithms. However, not much work has been published under the Bayesian framework. Read More

Quantum anomalous Hall (QAH) effect in magnetic topological insulator (TI) is a novel transport phenomenon in which the Hall resistance reaches the quantum plateau in the absence of external magnetic field. Recently, this exotic effect has been discovered experimentally in an ultrathin film of the Bi2Te3 family TI with spontaneous ferromagnetic (FM) order. An important question concerning the QAH state is whether it is simply a zero-magnetic-field version of the quantum Hall (QH) effect, or if there is new physics beyond the conventional paradigm. Read More

We propose an architecture for realizing quantum information transfer (QIT). In this architecture, a LC circuit is used to induce the necessary interaction between flux qubits, each magnetically coupling to a nitrogen-vacancy center ensemble (NVCE). We explicitly show that for resonant interaction and large detuning cases, high-fidelity QIT between two spatially-separated NVCEs can be implemented. Read More

We report transport studies on (Bi,Sb)2Te3 topological insulator thin films with tunable electronic band structure. We find a doping and temperature regime in which the Hall coefficient is negative indicative of electron-type carriers, whereas the Seebeck coefficient is positive indicative of hole-type carriers. This sign anomaly is due to the distinct transport behaviors of the bulk and surface states: the surface Dirac fermions dominate magnetoelectric transport while the thermoelectric effect is mainly determined by the bulk states. Read More

It is crucial for the studies of the transport properties and quantum effects related to Dirac surface states of three-dimensional topological insulators (3D TIs) to be able to simultaneously tune the chemical potentials of both top and bottom surfaces of a 3D TI thin film. We have realized this in molecular beam epitaxy-grown thin films of 3D TIs, as well as magnetic 3D TIs, by fabricating dual-gate structures on them. The films could be tuned between n-type and p-type by each gate alone. Read More

Measuring conditional dependence is an important topic in statistics with broad applications including graphical models. Under a factor model setting, a new conditional dependence measure based on projection is proposed. The corresponding conditional independence test is developed with the asymptotic null distribution unveiled where the number of factors could be high-dimensional. Read More

Quadratic regression (QR) models naturally extend linear models by considering interaction effects between the covariates. To conduct model selection in QR, it is important to maintain the hierarchical model structure between main effects and interaction effects. Existing regularization methods generally achieve this goal by solving complex optimization problems, which usually demands high computational cost and hence are not feasible for high dimensional data. Read More

Model selection is indispensable to high-dimensional sparse modeling in selecting the best set of covariates among a sequence of candidate models. Most existing work assumes implicitly that the model is correctly specified or of fixed dimensions. Yet model misspecification and high dimensionality are common in real applications. Read More

Stochastic blockmodels and variants thereof are among the most widely used approaches to community detection for social networks and relational data. A stochastic blockmodel partitions the nodes of a network into disjoint sets, called communities. The approach is inherently related to clustering with mixture models; and raises a similar model selection problem for the number of communities. Read More

Cavity-based large-scale quantum information processing (QIP) needs a large number of qubits and placing all of them in a single cavity quickly runs into many fundamental and practical problems such as the increase of cavity decay rate and decrease of qubit-cavity coupling strength. Therefore, future QIP most likely will require quantum networks consisting of a large number of cavities, each hosting and coupled to multiple qubits. In this work, we propose a way to prepare a $W$-class entangled state of spatially-separated multiple qubits in different cavities, which are connected to a coupler qubit. Read More

The Dirac-like surface states of the topological insulators (TIs) are protected by time reversal symmetry (TRS) and exhibit a host of novel properties. Introducing magnetism into TI, which breaks the TRS, is expected to create exotic topological magnetoelectric effects. A particularly intriguing phenomenon in this case is the magnetic field dependence of electrical resistance, or magnetoresistance (MR). Read More

We propose a simple method for realizing a multiqubit phase gate of one qubit simultaneously controlling $n$ target qubits, by using three-level quantum systems (i.e., qutrits) coupled to a cavity or resonator. Read More

We propose a high dimensional classification method that involves nonparametric feature augmentation. Knowing that marginal density ratios are the most powerful univariate classifiers, we use the ratio estimates to transform the original feature measurements. Subsequently, penalized logistic regression is invoked, taking as input the newly transformed or augmented features. Read More

Lasso has been both theoretically and empirically proved a successful variable selection approach. However, in the ultrahigh dimensional setting, the conditions of model selection consistency for lasso could easily fail. The independence screening framework tackles this problem by reducing the dimensionality based on marginal correlations before performing lasso. Read More

In this paper, for Lasso penalized linear regression models in high-dimensional settings, we propose a modified cross-validation method for selecting the penalty parameter. The methodology is extended to other penalties, such as Elastic Net. We conduct extensive simulation studies and real data analysis to compare the performance of the modified cross-validation method with other methods. Read More

Asymptotic behavior of the tuning parameter selection in the standard cross-validation methods is investigated for the high-dimensional variable selection problem. It is shown that the shrinkage problem with the Lasso penalty is not always the true reason for the over-selection phenomenon in the cross-validation based tuning parameter selection. After identifying the potential problems with the standard cross-validation methods, we propose a new procedure, Consistent Cross-Validation (CCV), for selecting the optimal tuning parameter. Read More

A new family of penalty functions, adaptive to likelihood, is introduced for model selection in general regression models. It arises naturally through assuming certain types of prior distribution on the regression parameters. To study stability properties of the penalized maximum likelihood estimator, two types of asymptotic stability are defined. Read More

Recently many regularized estimators of large covariance matrices have been proposed, and the tuning parameters in these estimators are usually selected via cross-validation. However, there is no guideline on the number of folds for conducting cross-validation and there is no comparison between cross-validation and the methods based on bootstrap. Through extensive simulations, we suggest 10-fold cross-validation (nine-tenths for training and one-tenth for validation) be appropriate when the estimation accuracy is measured in the Frobenius norm, while 2-fold cross-validation (half for training and half for validation) or reverse 3-fold cross-validation (one-third for training and two-thirds for validation) be appropriate in the operator norm. Read More

Motivated by modeling and analysis of mass-spectrometry data, a semi- and nonparametric model is proposed that consists of a linear parametric component for individual location and scale and a nonparametric regression function for the common shape. A multi-step approach is developed that simultaneously estimates the parametric components and the nonparametric function. Under certain regularity conditions, it is shown that the resulting estimators is consistent and asymptotic normal for the parametric part and achieve the optimal rate of convergence for the nonparametric part when the bandwidth is suitably chosen. Read More

In high-dimensional data analysis, penalized likelihood estimators are shown to provide superior results in both variable selection and parameter estimation. A new algorithm, APPLE, is proposed for calculating the Approximate Path for Penalized Likelihood Estimators. Both the convex penalty (such as LASSO) and the nonconvex penalty (such as SCAD and MCP) cases are considered. Read More

We propose a scheme to directly measure the exact value of geometric quantum discord of an arbitrary two-qubit state. We only need to perform the projective measurement in the all anti-symmetric subspace and our scheme is parametrically efficient in contrast to the widely adopted quantum state tomography scheme in the sense of less parameter estimations and projectors. Moreover, the present scheme can be easily realized with the current experimental techniques. Read More

We propose a theoretical scheme for realizing {\deg}exible two-qubit controlled phase gate. A transmission line resonator is used to induce the coupling between nitrogen-vacancy (N-V) in diamond and superconducting qubit. The N-V center acts as control qubit and the superconducting qubit as target qubit. Read More

We develop an architecture of hybrid quantum solid-state processing unit for universal quantum computing. The architecture allows distant and nonidentical solid-state qubits in distinct physical systems to interact and work collaboratively. All the quantum computing procedures are controlled by optical methods using classical fields and cavity QED. Read More

For high-dimensional classification, it is well known that naively performing the Fisher discriminant rule leads to poor results due to diverging spectra and noise accumulation. Therefore, researchers proposed independence rules to circumvent the diverse spectra, and sparse independence rules to mitigate the issue of noise accumulation. However, in biological applications, there are often a group of correlated genes responsible for clinical outcomes, and the use of the covariance information can significantly reduce misclassification rates. Read More

Estimation of genewise variance arises from two important applications in microarray data analysis: selecting significantly differentially expressed genes and validation tests for normalization of microarray data. We approach the problem by introducing a two-way nonparametric model, which is an extension of the famous Neyman--Scott model and is applicable beyond microarray data. The problem itself poses interesting challenges because the number of nuisance parameters is proportional to the sample size and it is not obvious how the variance function can be estimated when measurements are correlated. Read More

In this paper, the geometric and dynamic phase components of overall phase induced by 2{\pi} hyperbolic secant pulses in a quantum dot is analyzed. The dependence of two phase components on the ratio of the Rabi frequency to the detuning is investigated. Numerical results indicate that only for one resonant pulse the induced overall phase is purely the geometric phase. Read More

Variable selection in high dimensional space has challenged many contemporary statistical problems from many frontiers of scientific disciplines. Recent technology advance has made it possible to collect a huge amount of covariate information such as microarray, proteomic and SNP data via bioimaging technology while observing survival information on patients in clinical studies. Thus, the same challenge applies to the survival analysis in order to understand the association between genomics information and clinical information about the survival time. Read More

A variable screening procedure via correlation learning was proposed Fan and Lv (2008) to reduce dimensionality in sparse ultra-high dimensional models. Even when the true model is linear, the marginal regression can be highly nonlinear. To address this issue, we further extend the correlation learning to marginal nonparametric learning. Read More

Generalized linear models and the quasi-likelihood method extend the ordinary regression models to accommodate more general conditional distributions of the response. Nonparametric methods need no explicit parametric specification, and the resulting model is completely determined by the data themselves. However, nonparametric estimation schemes generally have a slower convergence rate such as the local polynomial smoothing estimation of nonparametric generalized linear models studied in Fan, Heckman and Wand [J. Read More

Graphical models are frequently used to explore networks, such as genetic networks, among a set of variables. This is usually carried out via exploring the sparsity of the precision matrix of the variables under consideration. Penalized likelihood methods are often used in such explorations. Read More