arXiv subjects

Qian Yu

Publications and source records attributed to Qian Yu.

144 records · Page 8Linked to original sources

arXiv2018

The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching

Many vision problems require matching images of object instances across different domains. These include fine-grained sketch-based image retrieval (FG-SBIR) and Person Re-identification (person ReID). Existing approaches attempt to learn a joint embedding space where images from different domains can be directly compared. In most cases, this space is defined by the output of the final layer of a deep neural network (DNN), which primarily contains features of a high semantic level. In this paper, we argue that both high and mid-level features are relevant for cross-domain instance matching (CDIM). Importantly, mid-level features already exist in earlier layers of the DNN. They just need to be extracted, represented, and fused properly with the final layer. Based on this simple but powerful idea, we propose a unified framework for CDIM. Instantiating our framework for FG-SBIR and ReID, we show that our simple models can easily beat the state-of-the-art models, which are often equipped with much more elaborate architectures.

cs.CV↗

arXiv2018

Limit theorems for functionals of two independent Gaussian processes

Under certain mild conditions, some limit theorems for functionals of two independent Gaussian processes are obtained. The results apply to general Gaussian processes including fractional Brownian motion, sub-fractional Brownian motion and bi-fractional Brownian motion. A new and interesting phenomenon is that, in comparison with the results for fractional Brownian motion, extra randomness appears in the limiting distributions for Gaussian processes with nonstationary increments, say sub-fractional Brownian motion and bi-fractional Brownian. The results are obtained based on the method of moments, in which Fourier analysis, the chaining argument introduced in \cite{nx1} and a paring technique are employed.

math.PR↗

arXiv2018

Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication

We consider a large-scale matrix multiplication problem where the computation is carried out using a distributed system with a master node and multiple worker nodes, where each worker can store parts of the input matrices. We propose a computation strategy that leverages ideas from coding theory to design intermediate computations at the worker nodes, in order to efficiently deal with straggling workers. The proposed strategy, named as \emph{polynomial codes}, achieves the optimum recovery threshold, defined as the minimum number of workers that the master needs to wait for in order to compute the output. Furthermore, by leveraging the algebraic structure of polynomial codes, we can map the reconstruction problem of the final output to a polynomial interpolation problem, which can be solved efficiently. Polynomial codes provide order-wise improvement over the state of the art in terms of recovery threshold, and are also optimal in terms of several other metrics. Furthermore, we extend this code to distributed convolution and show its order-wise optimality.

cs.IT↗

arXiv2017

Coded Fourier Transform

We consider the problem of computing the Fourier transform of high-dimensional vectors, distributedly over a cluster of machines consisting of a master node and multiple worker nodes, where the worker nodes can only store and process a fraction of the inputs. We show that by exploiting the algebraic structure of the Fourier transform operation and leveraging concepts from coding theory, one can efficiently deal with the straggler effects. In particular, we propose a computation strategy, named as coded FFT, which achieves the optimal recovery threshold, defined as the minimum number of workers that the master node needs to wait for in order to compute the output. This is the first code that achieves the optimum robustness in terms of tolerating stragglers or failures for computing Fourier transforms. Furthermore, the reconstruction process for coded FFT can be mapped to MDS decoding, which can be solved efficiently. Moreover, we extend coded FFT to settings including computing general $n$-dimensional Fourier transforms, and provide the optimal computing strategy for those settings.

cs.DC↗

arXiv2017

Transport in a Single Self-Doped Nanocrystal

Addressing the optical properties of a single nanoparticle in the infrared is particularly challenging, thus alternative methods for characterizing the conductance spectrum of nanoparticles in this spectral range need to be developed. Here we describe an efficient method of fabricating single nanoparticle tunnel junctions on a chip circuit. We apply this method to narrow band gap nanoparticles of HgSe, which band structure combine the inverted character of the bulk semimetal with quantum confinement and self-doping. Upon tuning the gate bias, measurement reveals the presence of two energy gaps in the spectrum. The wider gap results from the interband gap, while the narrower gap results from intraband transitions. The observation of the latter near zero gate voltage confirms the doped character of the nanoparticle at the single particle level, which is in full agreement with the ensemble optical and transport measurements. Finally we probe the phototransport within a single quantum dot and demonstrate a large photogain mechanism resulting from photogating.

cond-mat.mes-hall↗

arXiv2017

A Fundamental Tradeoff between Computation and Communication in Distributed Computing

How can we optimally trade extra computing power to reduce the communication load in distributed computing? We answer this question by characterizing a fundamental tradeoff between computation and communication in distributed computing, i.e., the two are inversely proportional to each other. More specifically, a general distributed computing framework, motivated by commonly used structures like MapReduce, is considered, where the overall computation is decomposed into computing a set of "Map" and "Reduce" functions distributedly across multiple computing nodes. A coded scheme, named "Coded Distributed Computing" (CDC), is proposed to demonstrate that increasing the computation load of the Map functions by a factor of $r$ (i.e., evaluating each function at $r$ carefully chosen nodes) can create novel coding opportunities that reduce the communication load by the same factor. An information-theoretic lower bound on the communication load is also provided, which matches the communication load achieved by the CDC scheme. As a result, the optimal computation-communication tradeoff in distributed computing is exactly characterized. Finally, the coding techniques of CDC is applied to the Hadoop TeraSort benchmark to develop a novel CodedTeraSort algorithm, which is empirically demonstrated to speed up the overall job execution by $1.97\times$ - $3.39\times$, for typical settings of interest.

cs.IT↗

arXiv2017

Attention-based Extraction of Structured Information from Street View Imagery

We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84.2% accuracy on the challenging French Street Name Signs (FSNS) dataset, significantly outperforming the previous state of the art (Smith'16), which achieved 72.46%. Furthermore, our new method is much simpler and more general than the previous approach. To demonstrate the generality of our model, we show that it also performs well on an even more challenging dataset derived from Google Street View, in which the goal is to extract business names from store fronts. Finally, we study the speed/accuracy tradeoff that results from using CNN feature extractors of different depths. Surprisingly, we find that deeper is not always better (in terms of accuracy, as well as speed). Our resulting model is simple, accurate and fast, allowing it to be used at scale on a variety of challenging real-world text extraction problems.

cs.CV↗

arXiv2017

A Scalable Framework for Wireless Distributed Computing

We consider a wireless distributed computing system, in which multiple mobile users, connected wirelessly through an access point, collaborate to perform a computation task. In particular, users communicate with each other via the access point to exchange their locally computed intermediate computation results, which is known as data shuffling. We propose a scalable framework for this system, in which the required communication bandwidth for data shuffling does not increase with the number of users in the network. The key idea is to utilize a particular repetitive pattern of placing the dataset (thus a particular repetitive pattern of intermediate computations), in order to provide coding opportunities at both the users and the access point, which reduce the required uplink communication bandwidth from users to access point and the downlink communication bandwidth from access point to users by factors that grow linearly with the number of users. We also demonstrate that the proposed dataset placement and coded shuffling schemes are optimal (i.e., achieve the minimum required shuffling load) for both a centralized setting and a decentralized setting, by developing tight information-theoretic lower bounds.

cs.IT↗

arXiv2017

How to Optimally Allocate Resources for Coded Distributed Computing?

Today's data centers have an abundance of computing resources, hosting server clusters consisting of as many as tens or hundreds of thousands of machines. To execute a complex computing task over a data center, it is natural to distribute computations across many nodes to take advantage of parallel processing. However, as we allocate more and more computing resources to a computation task and further distribute the computations, large amounts of (partially) computed data must be moved between consecutive stages of computation tasks among the nodes, hence the communication load can become the bottleneck. In this paper, we study the optimal allocation of computing resources in distributed computing, in order to minimize the total execution time in distributed computing accounting for both the duration of computation and communication phases. In particular, we consider a general MapReduce-type distributed computing framework, in which the computation is decomposed into three stages: \emph{Map}, \emph{Shuffle}, and \emph{Reduce}. We focus on a recently proposed \emph{Coded Distributed Computing} approach for MapReduce and study the optimal allocation of computing resources in this framework. For all values of problem parameters, we characterize the optimal number of servers that should be used for distributed processing, provide the optimal placements of the Map and Reduce tasks, and propose an optimal coded data shuffling scheme, in order to minimize the total execution time. To prove the optimality of the proposed scheme, we first derive a matching information-theoretic converse on the execution time, then we prove that among all possible resource allocation schemes that achieve the minimum execution time, our proposed scheme uses the exactly minimum possible number of servers.

cs.IT↗

arXiv2016

Finding the Optimal Demodulator Under Implementation Constraints

The common approach of designing a communication device is to maximize a well-defined objective function, e.g., the channel capacity and the cut-off rate. We propose easy-to-implement solutions for Gaussian channels that approximate the optimal results for these maximization problems. Three topics are addressed. First, we consider the case where the channel output is quantized, and we find the quantization thresholds that maximize the mutual information. The approximation derived from the asymptotic solution has a negligible loss on the entire range of SNR when 2-PAM modulation is used, and its quantization thresholds linearly depend on the standard deviation of noise. We also derive a simple estimator of the relative capacity loss due to quantization, based on the high-rate limit. Then we consider the integer constraint on the decoding metric, and maximize the mismatched channel capacity. We study the asymptotic solution of the optimal metric assignment and show that the same approximation we derived in the matched decoding case still holds for the mismatched decoder. Finally, we consider the demodulation problem for 8PSK bit-interleaved coded modulation(BICM). We derive the approximated optimal demodulation metrics that maximize the general cut-off rate or the mismatched capacity using max-log approximation . The error rate performances of the two metrics' assignments are compared, based on Reed-Solomon-Viterbi(RSV) code, and the mismatched capacity metric turns out to be better. The proposed approximation can be computed using an efficient firmware algorithm, and improves the system performance of commercial chips.

cs.IT↗

arXiv2016

Large Scale Business Discovery from Street Level Imagery

Search with local intent is becoming increasingly useful due to the popularity of the mobile device. The creation and maintenance of accurate listings of local businesses worldwide is time consuming and expensive. In this paper, we propose an approach to automatically discover businesses that are visible on street level imagery. Precise business store front detection enables accurate geo-location of businesses, and further provides input for business categorization, listing generation, etc. The large variety of business categories in different countries makes this a very challenging problem. Moreover, manual annotation is prohibitive due to the scale of this problem. We propose the use of a MultiBox based approach that takes input image pixels and directly outputs store front bounding boxes. This end-to-end learning approach instead preempts the need for hand modeling either the proposal generation phase or the post-processing phase, leveraging large labelled training datasets. We demonstrate our approach outperforms the state of the art detection techniques with a large margin in terms of performance and run-time efficiency. In the evaluation, we show this approach achieves human accuracy in the low-recall settings. We also provide an end-to-end evaluation of business discovery in the real world.

cs.CV↗

arXiv2015

Nanoscale Origins of the Damage Tolerance of the High-Entropy Alloy CrMnFeCoNi

Damage-tolerance can be an elusive characteristic of structural materials requiring both high strength and ductility, properties that are often mutually exclusive. High-entropy alloys are of interest in this regard. Specifically, the single-phase CrMnFeCoNi alloy displays tensile strength levels of ~1 GPa, excellent ductility (~60-70%) and exceptional fracture toughness (KJIc > 200 MPa/m). Here, through the use of in-situ straining in an aberration-corrected transmission electron microscope, we report on the salient atomistic to micro-scale mechanisms underlying the origin of these properties. We identify a synergy of multiple deformation mechanisms, rarely achieved in metallic alloys, which generates high strength, work hardening and ductility, including the easy motion of Shockley partials, their interactions to form stacking-fault parallelepipeds, and arrest at planar-slip bands of undissociated dislocations. We further show that crack propagation is impeded by twinned, nano-scale bridges that form between the near-tip crack faces and delay fracture by shielding the crack tip.

cond-mat.mtrl-sci↗

arXiv2015

Further Theoretical Study of Distribution Separation Method for Information Retrieval

Recently, a Distribution Separation Method (DSM) is proposed for relevant feedback in information retrieval, which aims to approximate the true relevance distribution by separating a seed irrelevance distribution from the mixture one. While DSM achieved a promising empirical performance, theoretical analysis of DSM is still need further study and comparison with other relative retrieval model. In this article, we first generalize DSM's theoretical property, by proving that its minimum correlation assumption is equivalent to the maximum (original and symmetrized) KL-Divergence assumption. Second, we also analytically show that the EM algorithm in a well-known Mixture Model is essentially a distribution separation process and can be simplified using the linear separation algorithm in DSM. Some empirical results are also presented to support our theoretical analysis.

cs.IR↗

arXiv2015

Sketch-a-Net that Beats Humans

We propose a multi-scale multi-channel deep neural network framework that, for the first time, yields sketch recognition performance surpassing that of humans. Our superior performance is a result of explicitly embedding the unique characteristics of sketches in our model: (i) a network architecture designed for sketch rather than natural photo statistics, (ii) a multi-channel generalisation that encodes sequential ordering in the sketching process, and (iii) a multi-scale network ensemble with joint Bayesian fusion that accounts for the different levels of abstraction exhibited in free-hand sketches. We show that state-of-the-art deep networks specifically engineered for photos of natural objects fail to perform well on sketch recognition, regardless whether they are trained using photo or sketch. Our network on the other hand not only delivers the best performance on the largest human sketch dataset to date, but also is small in size making efficient training possible using just CPUs.

cs.CV↗

arXiv2015

An optimal approximation of Rosenblatt sheet by multiple Wiener integrals

Let $Z^{α,β}$ be the Rosenblatt sheet with the representation $$ Z^{α,β}(t,s)=\int^t_0\int^s_0\int^t_0\int^s_0Q^α(t,y_1,y_2)Q^β(s,u_1,u_2)B(dy_1,du_1)B(dy_2,du_2) $$ where $B$ is a Brownian sheet, $\frac12<α,β<1$, $Q^α$ and $Q^β$ are the given kernel. In this paper, we contruct multiple Wiener integrals of the form \begin{align*} \int^t_0\int^s_0\int^t_0\int^s_0&[k_1(y_1,y_2)^{-\frac12α}(u_1,u_2)^{-\frac12β}+k_2(y_1\vee y_2)^{\frac12α}(y_1\wedge y_2)^{-\frac12α}|y_1-y_2|^{α-1}\\ &\cdot(u_1\vee u_2)^{\frac12β}(u_1\wedge u_2)^{-\frac12β}|u_1-u_2|^{β-1}]B(dy_1,du_1)B(dy_2,du_2),~~k_1,k_2\geq0, \end{align*} and obtain an optimal approximation of $Z^{α,β}(t,s)$.

math.PR↗

arXiv2014

Metal oxide resistive switching: evolution of the density of states across the metal-insulator transition

We report the study of metal-STO-metal memristors where the doping concentration in STO can be fine-tuned through electric field migration of oxygen vacancies. In this tunnel junction device, the evolution of the Density Of States (DoS) can be followed continuously across the Metal-Insulator Transition (MIT). At very low dopant concentration, the junction displays characteristic signatures of discrete dopants levels. As the dopant concentration increases, the semiconductor band gap fills in but a soft Coulomb gap remains. At even higher doping, a transition to a metallic state occurs where the DoS at the Fermi level becomes finite and Altshuler-Aronov corrections to the DoS are observed. At the critical point of the MIT, the DoS scales linearly with energy $N(\varepsilon) \sim \varepsilon$, the possible signature of multifractality.

cond-mat.mes-hall↗

arXiv2013

Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle

Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data. In this paper, we consider the dimensionality reduction in parameter spaces of binary multivariate distributions. We propose a general Confident-Information-First (CIF) principle to maximally preserve parameters with confident estimates and rule out unreliable or noisy parameters. Formally, the confidence of a parameter can be assessed by its Fisher information, which establishes a connection with the inverse variance of any unbiased estimate for the parameter via the Cramér-Rao bound. We then revisit Boltzmann machines (BM) and theoretically show that both single-layer BM without hidden units (SBM) and restricted BM (RBM) can be solidly derived using the CIF principle. This can not only help us uncover and formalize the essential parts of the target density that SBM and RBM capture, but also suggest that the deep neural network consisting of several layers of RBM can be seen as the layer-wise application of CIF. Guided by the theoretical analysis, we develop a sample-specific CIF-based contrastive divergence (CD-CIF) algorithm for SBM and a CIF-based iterative projection procedure (IP) for RBM. Both CD-CIF and IP are studied in a series of density estimation experiments.

cs.NE↗

arXiv2011

Pattern formation in oscillatory complex networks consisting of excitable nodes

Oscillatory dynamics of complex networks has recently attracted great attention. In this paper we study pattern formation in oscillatory complex networks consisting of excitable nodes. We find that there exist a few center nodes and small skeletons for most oscillations. Complicated and seemingly random oscillatory patterns can be viewed as well-organized target waves propagating from center nodes along the shortest paths, and the shortest loops passing through both the center nodes and their driver nodes play the role of oscillation sources. Analyzing simple skeletons we are able to understand and predict various essential properties of the oscillations and effectively modulate the oscillations. These methods and results will give insights into pattern formation in complex networks, and provide suggestive ideas for studying and controlling oscillations in neural networks.

nlin.CD↗