arXiv subjects

Qiang Liu

Publications and source records attributed to Qiang Liu.

At least 487 records · Page 27Linked to original sources

arXiv2017

Energy-efficient Amortized Inference with Cascaded Deep Classifiers

Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that optimizes the prediction accuracy and energy cost simultaneously, thus enabling effective cost-accuracy trade-off at test time. In our framework, each data instance is pushed into a cascade of deep neural networks with increasing sizes, and a selection module is used to sequentially determine when a sufficiently accurate classifier can be used for this data instance. The cascade of neural networks and the selection module are jointly trained in an end-to-end fashion by the REINFORCE algorithm to optimize a trade-off between the computational cost and the predictive accuracy. Our method is able to simultaneously improve the accuracy and efficiency by learning to assign easy instances to fast yet sufficiently accurate classifiers to save computation and energy cost, while assigning harder instances to deeper and more powerful classifiers to ensure satisfiable accuracy. With extensive experiments on several image classification datasets using cascaded ResNet classifiers, we demonstrate that our method outperforms the standard well-trained ResNets in accuracy but only requires less than 20% and 50% FLOPs cost on the CIFAR-10/100 datasets and 66% on the ImageNet dataset, respectively.

cs.LG↗

arXiv2017

Quantum simulation of general semi-classical Rabi model beyond strong driving regime

We propose a scheme to simulate the interaction between a two-level system and a classical light field. Under the transversal driving of two microwave tones, the system Hamiltonian is identical to that of the general semi-classical Rabi model. We experimentally realize this Hamiltonian with a superconducting transmon qubit. By tuning the strength, phase and frequency of the two microwave driving fields, we simulate the quantum dynamics from weak to extremely strong driving regime. The resulting evolutions gradually deviate from the normal sinusoidal Rabi oscillations with increasing driving strength, in accordance with the predictions of the general semi-classical Rabi model far beyond the weak driving limit. Our scheme provides an effective approach to investigate the extremely strong interaction between a two-level system and a classical light field. Such strong interactions are usually inaccessible in experiments.

quant-ph↗

arXiv2017

Leveraging local h-index to identify and rank influential spreaders in networks

Identifying influential nodes in complex networks has received increasing attention for its great theoretical and practical applications in many fields. Traditional methods, such as degree centrality, betweenness centrality, closeness centrality, and coreness centrality, have more or less disadvantages in detecting influential nodes, which have been illustrated in related literatures. Recently, the h-index, which is utilized to measure both the productivity and citation impact of the publications of a scientist or scholar, has been introduced to the network world to evaluate a node's spreading ability. However, this method assigns too many nodes with the same value, which leads to a resolution limit problem in distinguishing the real influence of these nodes. In this paper, we propose a local h-index centrality (LH-index) method for identifying and ranking influential nodes in networks. The LH-index method simultaneously takes into account of h-index values of the node itself and its neighbors, which is based on the idea that a node connects to more influential nodes will also be influential. According to the simulation results with the stochastic Susceptible-Infected-Recovered (SIR) model in four real world networks and several simulated networks, we demonstrate the effectivity of the LH-index method in identifying influential nodes in networks.

physics.soc-ph↗

arXiv2017

Stein Variational Adaptive Importance Sampling

We propose a novel adaptive importance sampling algorithm which incorporates Stein variational gradient decent algorithm (SVGD) with importance sampling (IS). Our algorithm leverages the nonparametric transforms in SVGD to iteratively decrease the KL divergence between our importance proposal and the target distribution. The advantages of this algorithm are twofold: first, our algorithm turns SVGD into a standard IS algorithm, allowing us to use standard diagnostic and analytic tools of IS to evaluate and interpret the results; second, we do not restrict the choice of our importance proposal to predefined distribution families like traditional (adaptive) IS methods. Empirical experiments demonstrate that our algorithm performs well on evaluating partition functions of restricted Boltzmann machines and testing likelihood of variational auto-encoders.

stat.ML↗

arXiv2017

Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE

We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generating realistic looking images. Our results suggest promising directions for learning better models by combining GAN-style methods with traditional energy-based learning.

stat.ML↗

arXiv2017

Mining Significant Microblogs for Misinformation Identification: An Attention-based Approach

With the rapid growth of social media, massive misinformation is also spreading widely on social media, such as microblog, and bring negative effects to human life. Nowadays, automatic misinformation identification has drawn attention from academic and industrial communities. For an event on social media usually consists of multiple microblogs, current methods are mainly based on global statistical features. However, information on social media is full of noisy and outliers, which should be alleviated. Moreover, most of microblogs about an event have little contribution to the identification of misinformation, where useful information can be easily overwhelmed by useless information. Thus, it is important to mine significant microblogs for a reliable misinformation identification method. In this paper, we propose an Attention-based approach for Identification of Misinformation (AIM). Based on the attention mechanism, AIM can select microblogs with largest attention values for misinformation identification. The attention mechanism in AIM contains two parts: content attention and dynamic attention. Content attention is calculated based textual features of each microblog. Dynamic attention is related to the time interval between the posting time of a microblog and the beginning of the event. To evaluate AIM, we conduct a series of experiments on the Weibo dataset and the Twitter dataset, and the experimental results show that the proposed AIM model outperforms the state-of-the-art methods.

cs.IR↗

arXiv2017

Approximate Inference with Amortised MCMC

We propose a novel approximate inference algorithm that approximates a target distribution by amortising the dynamics of a user-selected MCMC sampler. The idea is to initialise MCMC using samples from an approximation network, apply the MCMC operator to improve these samples, and finally use the samples to update the approximation network thereby improving its quality. This provides a new generic framework for approximate inference, allowing us to deploy highly complex, or implicitly defined approximation families with intractable densities, including approximations produced by warping a source of randomness through a deep neural network. Experiments consider image modelling with deep generative models as a challenging test for the method. Deep models trained using amortised MCMC are shown to generate realistic looking samples as well as producing diverse imputations for images with regions of missing pixels.

stat.ML↗

arXiv2017

Extensible 3D architecture for superconducting quantum computing

Using a multi-layered printed circuit board, we propose a 3D architecture suitable for packaging supercon- ducting chips, especially chips that contain two-dimensional qubit arrays. In our proposed architecture, the center strips of the buried coplanar waveguides protrude from the surface of a dielectric layer as contacts. Since the contacts extend beyond the surface of the dielectric layer, chips can simply be flip-chip packaged with on-chip receptacles clinging to the contacts. Using this scheme, we packaged a multi-qubit chip and per- formed single-qubit and two-qubit quantum gate operations. The results indicate that this 3D architecture provides a promising scheme for scalable quantum computing.

quant-ph↗

arXiv2017

Stein Variational Policy Gradient

Policy gradient methods have been successfully applied to many complex reinforcement learning problems. However, policy gradient methods suffer from high variance, slow convergence, and inefficient exploration. In this work, we introduce a maximum entropy policy optimization framework which explicitly encourages parameter exploration, and show that this framework can be reduced to a Bayesian inference problem. We then propose a novel Stein variational policy gradient method (SVPG) which combines existing policy gradient methods and a repulsive functional to generate a set of diverse but well-behaved policies. SVPG is robust to initialization and can easily be implemented in a parallel manner. On continuous control problems, we find that implementing SVPG on top of REINFORCE and advantage actor-critic algorithms improves both average return and data efficiency.

cs.LG↗

arXiv2017

Energy Efficient Joint Resource Allocation and Power Control for D2D Communications

In this paper, joint resource allocation and power control for energy efficient device-to-device (D2D) communications underlaying cellular networks are investigated. The resource and power are optimized for maximization of the energy efficiency (EE) of D2D communications. Exploiting the properties of fractional programming, we transform the original nonconvex optimization problem in fractional form into an equivalent optimization problem in subtractive form. Then, an efficient iterative resource allocation and power control scheme is proposed. In each iteration, part of the constraints of the EE optimization problem is removed by exploiting the penalty function approach. We further propose a novel two-layer approach which allows to find the optimum at each iteration by decoupling the EE optimization problem of joint resource allocation and power control into two separate steps. In the first layer, the optimal power values are obtained by solving a series of maximization problems through root-finding with or without considering the loss of cellular users' rates. In the second layer, the formulated optimization problem belongs to a classical resource allocation problem with single allocation format which admits a network flow formulation so that it can be solved to optimality. Simulation results demonstrate the remarkable improvements in terms of EE by using the proposed iterative resource allocation and power control scheme.

cs.IT↗

arXiv2017

Bootstrap Model Aggregation for Distributed Statistical Learning

In distributed, or privacy-preserving learning, we are often given a set of probabilistic models estimated from different local repositories, and asked to combine them into a single model that gives efficient statistical estimation. A simple method is to linearly average the parameters of the local models, which, however, tends to be degenerate or not applicable on non-convex models, or models with different parameter dimensions. One more practical strategy is to generate bootstrap samples from the local models, and then learn a joint model based on the combined bootstrap set. Unfortunately, the bootstrap procedure introduces additional noise and can significantly deteriorate the performance. In this work, we propose two variance reduction methods to correct the bootstrap noise, including a weighted M-estimator that is both statistically efficient and practically powerful. Both theoretical and empirical analysis is provided to demonstrate our methods.

stat.ML↗

arXiv2017

Realizing and manipulating space-time inversion symmetric topological semimetal bands with superconducting quantum circuits

We have experimentally realized novel space-time inversion (P-T) invariant Z2-type topological semimetal-bands, via an analogy between the momentum space and a controllable parameter space in superconducting quantum circuits. By measuring the whole energy spectrum of system, we imaged clearly an exotic tunable gapless band structure of topological semimetals. Two topological quantum phase transitions from a topological semimetal to two kinds of insulators can be manipulated by continuously tuning the different parameters in the experimental setup, one of which captures the Z2 topology of the PT semimetal via merging a pair of nontrivial Z2 Dirac points. Remarkably, the topological robustness was demonstrated unambiguously, by adding a perturbation that breaks only the individual T and P symmetries but keeps the joint PT symmetry. In contrast, when another kind of PT -violated perturbation is introduced, a topologically trivial insulator gap is fully opened.

quant-ph↗

arXiv2017

Multi-behavioral Sequential Prediction with Recurrent Log-bilinear Model

With the rapid growth of Internet applications, sequential prediction in collaborative filtering has become an emerging and crucial task. Given the behavioral history of a specific user, predicting his or her next choice plays a key role in improving various online services. Meanwhile, there are more and more scenarios with multiple types of behaviors, while existing works mainly study sequences with a single type of behavior. As a widely used approach, Markov chain based models are based on a strong independence assumption. As two classical neural network methods for modeling sequences, recurrent neural networks cannot well model short-term contexts, and the log-bilinear model is not suitable for long-term contexts. In this paper, we propose a Recurrent Log-BiLinear (RLBL) model. It can model multiple types of behaviors in historical sequences with behavior-specific transition matrices. RLBL applies a recurrent structure for modeling long-term contexts. It models several items in each hidden layer and employs position-specific transition matrices for modeling short-term contexts. Moreover, considering continuous time difference in behavioral history is a key factor for dynamic prediction, we further extend RLBL and replace position-specific transition matrices with time-specific transition matrices, and accordingly propose a Time-Aware Recurrent Log-BiLinear (TA-RLBL) model. Experimental results show that the proposed RLBL model and TA-RLBL model yield significant improvements over the competitive compared methods on three datasets, i.e., Movielens-1M dataset, Global Terrorism Database and Tmall dataset with different numbers of behavior types.

cs.IR↗

arXiv2017

Variable Stars Observed in the Galactic Disk by AST3-1 from Dome A, Antarctica

AST3-1 is the second-generation wide-field optical photometric telescope dedicated to time domain astronomy at Dome A, Antarctica. Here we present the results of $i$ band images survey from AST3-1 towards one Galactic disk field. Based on time-series photometry of 92,583 stars, 560 variable stars were detected with $i$ magnitude $\leq$ 16.5 mag during eight days of observations; 339 of these are previously unknown variables. We tentatively classify the 560 variables as 285 eclipsing binaries (EW, EB, EA), 27 pulsating variable stars ($δ$~Scuti, $γ$~Doradus, $δ$~Cephei variable and RR Lyrae stars) and 248 other types of variables (unclassified periodic, multi-periodic and aperiodic variable stars). Among the eclipsing binaries, 34 show O'Connell effects. One of the aperiodic variables shows a plateau light curve and another one shows a secondary maximum after peak brightness. We also detected a complex binary system with RS CVn-like light curve morphology; this object is being followed-up spectroscopically using the Gemini South telescope.

astro-ph.IM↗

arXiv2016

Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient that maximumly decreases the KL divergence with the target distribution. Our method works for any target distribution specified by their unnormalized density function, and can train any black-box architectures that are differentiable in terms of the parameters we want to adapt. As an application of our method, we propose an amortized MLE algorithm for training deep energy model, where a neural sampler is adaptively trained to approximate the likelihood function. Our method mimics an adversarial game between the deep energy model and the neural sampler, and obtains realistic-looking images competitive with the state-of-the-art results.

stat.ML↗

arXiv2016

ICE: Information Credibility Evaluation on Social Media via Representation Learning

With the rapid growth of social media, rumors are also spreading widely on social media and bring harm to people's daily life. Nowadays, information credibility evaluation has drawn attention from academic and industrial communities. Current methods mainly focus on feature engineering and achieve some success. However, feature engineering based methods require a lot of labor and cannot fully reveal the underlying relations among data. In our viewpoint, the key elements of user behaviors for evaluating credibility are concluded as "who", "what", "when", and "how". These existing methods cannot model the correlation among different key elements during the spreading of microblogs. In this paper, we propose a novel representation learning method, Information Credibility Evaluation (ICE), to learn representations of information credibility on social media. In ICE, latent representations are learnt for modeling user credibility, behavior types, temporal properties, and comment attitudes. The aggregation of these factors in the microblog spreading process yields the representation of a user's behavior, and the aggregation of these dynamic representations generates the credibility representation of an event spreading on social media. Moreover, a pairwise learning method is applied to maximize the credibility difference between rumors and non-rumors. To evaluate the performance of ICE, we conduct experiments on a Sina Weibo data set, and the experimental results show that our ICE model outperforms the state-of-the-art methods.

cs.SI↗

arXiv2016

Black-box Importance Sampling

Importance sampling is widely used in machine learning and statistics, but its power is limited by the restriction of using simple proposals for which the importance weights can be tractably calculated. We address this problem by studying black-box importance sampling methods that calculate importance weights for samples generated from any unknown proposal or black-box mechanism. Our method allows us to use better and richer proposals to solve difficult problems, and (somewhat counter-intuitively) also has the additional benefit of improving the estimation accuracy beyond typical importance sampling. Both theoretical and empirical analyses are provided.

stat.ML↗

arXiv2016

Die-out Probability in SIS Epidemic Processes on Networks

An accurate approximate formula of the die-out probability in a SIS epidemic process on a network is proposed. The formula contains only three essential parameters: the largest eigenvalue of the adjacency matrix of the network, the effective infection rate of the virus, and the initial number of infected nodes in the network. The die-out probability formula is compared with the exact die-out probability in complete graphs, Erdős-Rényi graphs, and a power-law graph. Furthermore, as an example, the formula is applied to the $N$-Intertwined Mean-Field Approximation, to explicitly incorporate the die-out.

cs.SI↗