Searcharxiv⌕ Search

arXiv subjects

Xiao Chen

Publications and source records attributed to Xiao Chen.

At least 307 records · Page 17Linked to original sources
arXiv2019

Advanced Variations of Two-Dimensional Principal Component Analysis for Face Recognition

The two-dimensional principal component analysis (2DPCA) has become one of the most powerful tools of artificial intelligent algorithms. In this paper, we review 2DPCA and its variations, and propose a general ridge regression model to extract features from both row and column directions. To enhance the generalization ability of extracted features, a novel relaxed 2DPCA (R2DPCA) is proposed with a new ridge regression model. R2DPCA generates a weighting vector with utilizing the label information, and maximizes a relaxed criterion with applying an optimal algorithm to get the essential features. The R2DPCA-based approaches for face recognition and image reconstruction are also proposed and the selected principle components are weighted to enhance the role of main components. Numerical experiments on well-known standard databases indicate that R2DPCA has high generalization ability and can achieve a higher recognition rate than the state-of-the-art methods, including in the deep learning methods such as CNNs, DBNs, and DNNs.

cs.CV↗
arXiv2019

Dialog State Tracking with Reinforced Data Augmentation

Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate high-quality data to improve the neural state tracker. Specifically, we introduce a novel contextual bandit generator to learn fine-grained augmentation policies that can generate new effective instances by choosing suitable replacements for the specific context. Moreover, by alternately learning between the generator and the state tracker, we can keep refining the generative policies to generate more high-quality training data for neural state tracker. Experimental results on the WoZ and MultiWoZ (restaurant) datasets demonstrate that the proposed framework significantly improves the performance over the state-of-the-art models, especially with limited training data.

cs.CL↗
arXiv2019

Energy Resource Control via Privacy Preserving Data

Although the frequent monitoring of smart meters enables granular control over energy resources, it also increases the risk of leakage of private information such as income, home occupancy, and power consumption behavior that can be inferred from the data by an adversary. We propose a method of releasing modified smart meter data so specific private attributes are obscured while the utility of the data for use in an energy resource controller is preserved. The method achieves privatization by injecting noise conditional on the private attribute through a linear filter learned via a minimax optimization. The optimization contains the loss function of a classifier for the private attribute, which we maximize, and the energy resource controller's objective formulated as a canonical form optimization, which we minimize. We perform our experiment on a dataset of household consumption with solar generation and another from the Commission for Energy Regulation that contains household smart meter data with sensitive attributes such as income and home occupancy. We demonstrate that our method is able to significantly reduce the ability of an adversary to classify the private attribute while maintaining a similar objective value for an energy storage controller.

eess.SY↗
arXiv2019

Measurement-driven entanglement transition in hybrid quantum circuits

In this paper we continue to explore "hybrid" quantum circuit models in one-dimension with both unitary and measurement gates, focussing on the entanglement properties of wavefunction trajectories at long times, in the steady state. We simulate a large class of Clifford circuits, including models with or without randomness in the unitary gates, and with or without randomness in the locations of measurement gates, using stabilizer techniques to access the long time dynamics of systems up to 512 qubits. In all models we find a volume law entangled phase for low measurement rates, which exhibits a sub-dominant logarithmic behavior in the entanglement entropy, $S_A = α \ln |A| + s|A|$, with sub-system size $|A|$. With increasing measurement rate the volume law phase is unstable to a disentangled area law phase, passing through a single entanglement transition at a critical rate of measurement. At criticality we find a purely logarithmic entanglement entropy, $S_A = α(p_c) \ln|A|$, a power law decay and conformal symmetry of the mutual information, with exponential decay off criticality. Various spin-spin correlation functions also show slow decay at criticality. Critical exponents are consistent across all models, indicative of a single universality class. These results suggest the existence of an effective underlying statistical mechanical model for the entanglement transition. Beyond Clifford circuit models, numerical simulations of up to 20 qubits give consistent results.

cond-mat.stat-mech↗
arXiv2019

Uncertainty Quantification in Stochastic Economic Dispatch using Gaussian Process Emulation

The increasing penetration of renewable energy resources in power systems, represented as random processes, converts the traditional deterministic economic dispatch problem into a stochastic one. To solve this stochastic economic dispatch, the conventional Monte Carlo method is prohibitively time consuming for medium- and large-scale power systems. To overcome this problem, we propose in this paper a novel Gaussian-process-emulator-based approach to quantify the uncertainty in the stochastic economic dispatch considering wind power penetration. Based on the dimension-reduction results obtained by the Karhunen-Loève expansion, a Gaussian-process emulator is constructed. This surrogate allows us to evaluate the economic dispatch solver at sampled values with a negligible computational cost while maintaining a desirable accuracy. Simulation results conducted on the IEEE 118-bus system reveal that the proposed method has an excellent performance as compared to the traditional Monte Carlo method.

eess.SY↗
arXiv2019

Quantum chaos dynamics in long-range power law interaction systems

We use out-of-time-order commutator (OTOC) to diagnose the propagation of chaos in one dimensional long-range power law interaction system. We map the evolution of OTOC to a classical stochastic dynamics problem and use a Brownian quantum circuit to exactly derive the master equation. We vary two parameters: the number of qubits $N$ on each site (the onsite Hilbert space dimension) and the power law exponent $α$. Three light cone structures of OTOC appear at $N = 1$: (1) logarithmic when $0.5<α\lesssim 0.8$, (2) sublinear power law when $0.8 \lesssim α\lesssim 1.5$ and (3) linear when $α\gtrsim 1.5$. The OTOC scales as $\exp(λt)/x^{2α} $ and $t^{2 α/ ζ} / x^{ 2 α} $ respectively beyond the light cones in the first two cases. When $α\geq 2$, the OTOC has essentially the same diffusive broadening as systems with short-range interactions, suggesting a complete recovery of locality. In the large $N$ limit, it is always a logarithmic light cone asymptotically, although a linear light cone can appear before the transition time for $ α\gtrsim 1.5$. This implies the locality is never fully recovered for finite $α$. Our result provides a unified physical picture for the chaos dynamics in long-range power law interaction system.

cond-mat.stat-mech↗
arXiv2019

Evolution of entanglement spectra under generic quantum dynamics

We characterize the early stages of the approach to equilibrium in isolated quantum systems through the evolution of the entanglement spectrum. We find that the entanglement spectrum of a subsystem evolves with at least three distinct timescales. First, on an o(1) timescale, independent of system or subsystem size and the details of the dynamics, the entanglement spectrum develops nearest-neighbor level repulsion. The second timescale sets in when the light-cone has traversed the subsystem. Between these two times, the density of states of the reduced density matrix takes a universal, scale-free 1/f form; thus, random-matrix theory captures the local statistics of the entanglement spectrum but not its global structure. The third time scale is that on which the entanglement saturates; this occurs well after the light-cone traverses the subsystem. Between the second and third times, the entanglement spectrum compresses to its thermal Marchenko-Pastur form. These features hold for chaotic Hamiltonian and Floquet dynamics as well as a range of quantum circuit models.

cond-mat.dis-nn↗
arXiv2019

Brain Segmentation from k-space with End-to-end Recurrent Attention Network

The task of medical image segmentation commonly involves an image reconstruction step to convert acquired raw data to images before any analysis. However, noises, artifacts and loss of information due to the reconstruction process are almost inevitable, which compromises the final performance of segmentation. We present a novel learning framework that performs magnetic resonance brain image segmentation directly from k-space data. The end-to-end framework consists of a unique task-driven attention module that recurrently utilizes intermediate segmentation estimation to facilitate image-domain feature extraction from the raw data, thus closely bridging the reconstruction and the segmentation tasks. In addition, to address the challenge of manual labeling, we introduce a novel workflow to generate labeled training data for segmentation by exploiting imaging modality simulators and digital phantoms. Extensive experimental results show that the proposed method outperforms several state-of-the-art methods.

cs.CV↗
arXiv2019

News Cover Assessment via Multi-task Learning

Online personalized news product needs a suitable cover for the article. The news cover demands to be with high image quality, and draw readers' attention at same time, which is extraordinary challenging due to the subjectivity of the task. In this paper, we assess the news cover from image clarity and object salience perspective. We propose an end-to-end multi-task learning network for image clarity assessment and semantic segmentation simultaneously, the results of which can be guided for news cover assessment. The proposed network is based on a modified DeepLabv3+ model. The network backbone is used for multiple scale spatial features exaction, followed by two branches for image clarity assessment and semantic segmentation, respectively. The experiment results show that the proposed model is able to capture important content in images and performs better than single-task learning baselines on our proposed game content based CIA dataset.

cs.CV↗
arXiv2019

Understanding Video Content: Efficient Hero Detection and Recognition for the Game "Honor of Kings"

In order to understand content and automatically extract labels for videos of the game "Honor of Kings", it is necessary to detect and recognize characters (called "hero") together with their camps in the game video. In this paper, we propose an efficient two-stage algorithm to detect and recognize heros in game videos. First, we detect all heros in a video frame based on blood bar template-matching method, and classify them according to their camps (self/ friend/ enemy). Then we recognize the name of each hero using one or more deep convolution neural networks. Our method needs almost no work for labelling training and testing samples in the recognition stage. Experiments show its efficiency and accuracy in the task of hero detection and recognition in game videos.

cs.CV↗
arXiv2019

Electric vehicle charging during the day or at night: a perspective on carbon emissions

We propose an emission-oriented charging scheme to evaluate the emissions of electric vehicle (EV) charging from the electricity sector at the region of Electric Reliability Council of Texas (ERCOT). We investigate both day- and night-charging scenarios combined with realistic system load demand under the emission-oriented vs direct charging schemes. Our emission-oriented charging scheme reduces carbon emissions in the day by 13.8% on average. We also find that emission-oriented charging results in a significant CO2 reduction in 30% of the days in a year compared with direct charging. Apart from offering a flat rebate for EV owners, our analysis reveals that certain policy incentives (e.g. pricing) regarding EV charging should be taken into account in order to reflect the benefits of emissions reduction that haven't been incorporated in the current market of electricity transactions.

eess.SY↗
arXiv2019

Modeling Semantic Compositionality with Sememe Knowledge

Semantic compositionality (SC) refers to the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents. Most related works focus on using complicated compositionality functions to model SC while few works consider external knowledge in models. In this paper, we verify the effectiveness of sememes, the minimum semantic units of human languages, in modeling SC by a confirmatory experiment. Furthermore, we make the first attempt to incorporate sememe knowledge into SC models, and employ the sememeincorporated models in learning representations of multiword expressions, a typical task of SC. In experiments, we implement our models by incorporating knowledge from a famous sememe knowledge base HowNet and perform both intrinsic and extrinsic evaluations. Experimental results show that our models achieve significant performance boost as compared to the baseline methods without considering sememe knowledge. We further conduct quantitative analysis and case studies to demonstrate the effectiveness of applying sememe knowledge in modeling SC. All the code and data of this paper can be obtained on https://github.com/thunlp/Sememe-SC.

cs.CL↗
arXiv2019

Generative Adversarial Privacy

We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP's performance on the GENKI face database.

cs.LG↗
arXiv2019

Operator Dynamics in Brownian Quantum Circuit

We explore the operator dynamics in a random $N$-spin model with pairwise interactions (Brownian quanum circuit). We introduce the height $h$ of an operator to characterize its spatial extent, and derive the master equation of the height probability distribution. The study of an initial simple operator with $h = 1$ (minimal nonzero height) shows that the mean height, which is proportional to the squared commutator, has an initial exponential growth. It then slows down around the scrambling time $\sim\log N$ and finally saturates to a steady state in a manner similar to the logistic function. The deviation to the logistic function is due to the large fluctuations (order $N$) in the intermediate time. Moreover, we find that the exponential growth rate (quantum Lyapunov exponent) is smaller for initial operator with $\langle h\rangle\gg 1$. Based on this observation, we propose that the chaos bound at finite temperature can be produced by an initial operator whose height distribution is biased towards higher operators. We numerically test the power law initial height distribution $1/h^α $ in a Brownian circuit with number of spin $N=10000$ and show that the Lyapunov exponent is linearly constrained by $α$ before reaching the infinite temperature value.

cond-mat.str-el↗
arXiv2019

Relaxed 2-D Principal Component Analysis by $L_p$ Norm for Face Recognition

A relaxed two dimensional principal component analysis (R2DPCA) approach is proposed for face recognition. Different to the 2DPCA, 2DPCA-$L_1$ and G2DPCA, the R2DPCA utilizes the label information (if known) of training samples to calculate a relaxation vector and presents a weight to each subset of training data. A new relaxed scatter matrix is defined and the computed projection axes are able to increase the accuracy of face recognition. The optimal $L_p$-norms are selected in a reasonable range. Numerical experiments on practical face databased indicate that the R2DPCA has high generalization ability and can achieve a higher recognition rate than state-of-the-art methods.

cs.CV↗
arXiv2019

Distributed generation of privacy preserving data with user customization

Distributed devices such as mobile phones can produce and store large amounts of data that can enhance machine learning models; however, this data may contain private information specific to the data owner that prevents the release of the data. We wish to reduce the correlation between user-specific private information and data while maintaining the useful information. Rather than learning a large model to achieve privatization from end to end, we introduce a decoupling of the creation of a latent representation and the privatization of data that allows user-specific privatization to occur in a distributed setting with limited computation and minimal disturbance on the utility of the data. We leverage a Variational Autoencoder (VAE) to create a compact latent representation of the data; however, the VAE remains fixed for all devices and all possible private labels. We then train a small generative filter to perturb the latent representation based on individual preferences regarding the private and utility information. The small filter is trained by utilizing a GAN-type robust optimization that can take place on a distributed device. We conduct experiments on three popular datasets: MNIST, UCI-Adult, and CelebA, and give a thorough evaluation including visualizing the geometry of the latent embeddings and estimating the empirical mutual information to show the effectiveness of our approach.

cs.LG↗
arXiv2018

Multiple topological transitions in twisted bilayer graphene near the first magic angle

Recent experiments have observed strongly correlated physics in twisted bilayer graphene (TBG) at very small angles, along with nearly flat electron bands at certain fillings. A good starting point in understanding the physics is a continuum model (CM) proposed by Lopes dos Santos et al. [Phys. Rev. Lett. 99, 256802 (2007)] and Bistritzer et al. [PNAS 108, 12233 (2011)] for TBG at small twist angles, which successfully predicts the bandwidth reduction of the middle two bands of TBG near the first magic angle $θ_0=1.05^\circ$. In this paper, we analyze the symmetries of the CM and investigate the low energy flat band structure in the entire moiré Brillouin zone near $θ_0$. Instead of observing flat bands at only one "magic" angle, we notice that the bands remain almost flat within a small range around $θ_0$, where multiple topological transitions occur. The topological transitions are caused by the creation and annihilation of Dirac nodes at either $\text{K}$, $\text{K}^\prime$, or $Γ$ points, or along the high symmetry lines in the moiré Brillouin zone. We trace the evolution of the nodes and find that there are several processes transporting them from $Γ$ to $\text{K}$ and $\text{K}^\prime$. At the $Γ$ point, the lowest energy levels of the CM are doubly degenerate for some range of twisting angle around $θ_0$, suggesting that the physics is not described by any two band model. Based on this observation, we propose an effective six-band model (up to second order in quasi-momentum) near the $Γ$ point with the full symmetries of the CM, which we argue is the minimal model that explains the motion of the Dirac nodes around $Γ$ as the twist angle is varied. By fitting the coefficients from the numerical results, we show that this six-band model captures the important physics over a wide range of angles near the first "magic" angle.

cond-mat.str-el↗