Still searching Arxiv, refresh for possibly better results.

total 43980took 0.13s

Simultaneous Estimation of Number of Clusters and Feature Sparsity in Clustering High-Dimensional DataSep 04 2019Estimating the number of clusters (K) is a critical and often difficult task in cluster analysis. Many methods have been proposed to estimate K, including some top performers using resampling approach. When performing cluster analysis in high-dimensional ... More

GM-Net: Learning Features with More EfficiencyJun 21 2017Deep Convolutional Neural Networks (CNNs) are capable of learning unprecedentedly effective features from images. Some researchers have struggled to enhance the parameters' efficiency using grouped convolution. However, the relation between the optimal ... More

Fast Training of Sparse Graph Neural Networks on Dense HardwareJun 27 2019Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by operating on a sparse representation of graph adjacency matrices. As we ... More

Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health RecordsJun 11 2019Jun 28 2019Effective modeling of electronic health records (EHR) is rapidly becoming an important topic in both academia and industry. A recent study showed that utilizing the graphical structure underlying EHR data (e.g. relationship between diagnoses and treatments) ... More

All-optical wavelength-tunable narrow-linewidth fiber laserDec 12 2017Parameter regulations of narrow-linewidth fiber lasers in frequency domain has drawn considerable interests for widespread applications in the light quantum computing, precise coherent detection, and generation of micro-waves. All-optical methods provide ... More

The Closest Point Method and multigrid solvers for elliptic equations on surfacesJul 16 2013Oct 27 2014Elliptic partial differential equations are important both from application and analysis points of views. In this paper we apply the Closest Point Method to solving elliptic equations on general curved surfaces. Based on the closest point representation ... More

Generative Moment Matching NetworksFeb 10 2015We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative adversarial networks ... More

Pileup Subtraction and Jet Energy Prediction Using Machine LearningDec 15 2015Dec 16 2015In the Large Hardron Collider (LHC), multiple proton-proton collisions cause pileup in reconstructing energy information for a single primary collision (jet). This project aims to select the most important features and create a model to accurately estimate ... More

Learning unbiased featuresDec 17 2014A key element in transfer learning is representation learning; if representations can be developed that expose the relevant factors underlying the data, then new tasks and domains can be learned readily based on mappings of these salient factors. We propose ... More

Maximum matchings and minimum dominating sets in Apollonian networks and extended Tower of Hanoi graphsSep 13 2017The Apollonian networks display the remarkable power-law and small-world properties as observed in most realistic networked systems. Their dual graphs are extended Tower of Hanoi graphs, which are obtained from the Tower of Hanoi graphs by adding a special ... More

Deep speckle correlation: a deep learning approach towards scalable imaging through scattering mediaJun 11 2018Sep 26 2018Imaging through scattering is an important, yet challenging problem. Tremendous progress has been made by exploiting the deterministic input-output "transmission matrix" for a fixed medium. However, this "one-to-one" mapping is highly susceptible to speckle ... More

Watt-level, all-fiber, ultrafast Er/Yb-codoped double-clad fiber laser mode-locked by reduced graphene oxide interacting with a weak evanescent fieldMar 12 2015We propose a Watt-level, all-fiber, ultrafast Er/Yb-codoped double-clad fiber laser passively mode-locked by reduced graphene oxide (rGO) interacting with a weak evanescent field of photonic crystal fiber (PCF). The rGO solution is filled into the cladding ... More

Graph Matching Networks for Learning the Similarity of Graph Structured ObjectsApr 29 2019May 12 2019This paper addresses the challenging problem of retrieval and matching of graph structured objects, and makes two key contributions. First, we demonstrate how Graph Neural Networks (GNN), which have emerged as an effective model for various supervised ... More

Reliable deep-learning-based phase imaging with uncertainty quantificationJan 07 2019May 05 2019Emerging deep-learning (DL)-based techniques have significant potential to revolutionize biomedical imaging. However, one outstanding challenge is the lack of reliability assessment in the DL predictions, whose errors are commonly revealed only in hindsight. ... More

Electric-field Control of Magnetism with Emergent Topological Hall Effect in SrRuO3 through Proton EvolutionNov 27 2018Ionic substitution forms an essential pathway to manipulate the carrier density and crystalline symmetry of materials via ion-lattice-electron coupling, leading to a rich spectrum of electronic states in strongly correlated systems. Using the ferromagnetic ... More

Gated Graph Sequence Neural NetworksNov 17 2015May 03 2016Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work ... More

Learning Deep Generative Models of GraphsMar 08 2018Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful new approach ... More

Rare geometries: revealing rare categories via dimension-driven statisticsJan 29 2019May 28 2019In many situations, classes of data points of primary interest also happen to be those that are least numerous. A well-known example is detection of fraudulent transactions among the collection of all financial transactions, the vast majority of which ... More

The Variational Fair AutoencoderNov 03 2015Aug 10 2017We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a variational autoencoding ... More

Illumination coding meets uncertainty learning: toward reliable AI-augmented phase imagingJan 07 2019Apr 09 2019We develop a new Bayesian convolutional neural network (BNN) based technique for achieving large space-bandwidth product phase imaging that is both scalable and reliable. The scalability of our technique is enabled by a novel coded illumination scheme ... More

Graph Matching Networks for Learning the Similarity of Graph Structured ObjectsApr 29 2019This paper addresses the challenging problem of retrieval and matching of graph structured objects, and makes two key contributions. First, we demonstrate how Graph Neural Networks (GNN), which have emerged as an effective model for various supervised ... More

Optical-controlled wavelength-tunable Q-switched mode-locked fiber laser based on graphene-deposited micro-FBGApr 21 2017We report a wavelength-tunable Q-switched mode-locked fiber laser based on a compact optical tuning device, which is fabricated by coating single-layer graphene on the surface of micro-fiber Bragg grating (MFBG). Based on thermal-optical effect through ... More

The Variational Fair AutoencoderNov 03 2015Feb 04 2016We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a variational autoencoding ... More

Illumination coding meets uncertainty learning: toward reliable AI-augmented phase imagingJan 07 2019Feb 26 2019We propose a physics-guided deep learning (DL) framework for large space-bandwidth product (SBP) phase imaging. We design an asymmetric coded illumination scheme to encode high-resolution phase information across a wide field-of-view. We then develop ... More

Proximal Policy Optimization and its Dynamic Version for Sequence GenerationAug 24 2018In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this ... More

Detecting Violence in Video using SubclassesApr 27 2016This paper attacks the challenging problem of violence detection in videos. Different from existing works focusing on combining multi-modal features, we go one step further by adding and exploiting subclasses visually related to violence. We enrich the ... More

Enhanced Attacks on Defensively Distilled Deep Neural NetworksNov 16 2017Deep neural networks (DNNs) have achieved tremendous success in many tasks of machine learning, such as the image classification. Unfortunately, researchers have shown that DNNs are easily attacked by adversarial examples, slightly perturbed images which ... More

Understanding the Effective Receptive Field in Deep Convolutional Neural NetworksJan 15 2017Jan 25 2017We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. ... More

Deep learning approach to Fourier ptychographic microscopyApr 27 2018Jul 30 2018Convolutional neural networks (CNNs) have gained tremendous success in solving complex inverse problems. The aim of this work is to develop a novel CNN framework to reconstruct video sequence of dynamic live cells captured using a computational microscopy ... More

A protonated brownmillerite electrolyte for superior low-temperature proton conductivityNov 27 2018Design novel solid oxide electrolyte with enhanced ionic conductivity forms one of the Holy Grails in the field of materials science due to its great potential for wide range of energy applications. Conventional solid oxide electrolyte typically requires ... More

REGAL: Transfer Learning For Fast Optimization of Computation GraphsMay 07 2019We present a deep reinforcement learning approach to optimizing the execution cost of computation graphs in a static compiler. The key idea is to combine a neural network policy with a genetic algorithm, the Biased Random-Key Genetic Algorithm (BRKGA). ... More

Evidence of charge density wave with anisotropic gap in monolayer VTe$_2$ filmMay 31 2019We report experimental evidence of charge density wave (CDW) transition in monolayer 1T-VTe$_2$ film. 4$\times$4 reconstruction peaks are observed by low energy electron diffraction below the transition temperature $T_{CDW}$ = 186 K. Angle-resolved photoemission ... More

Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health RecordsJun 11 2019Effective modeling of electronic health records (EHR) is rapidly becoming an important topic in both academia and industry. A recent study showed that utilizing the graphical structure underlying EHR data (e.g. relationship between diagnoses and treatments) ... More

REGAL: Transfer Learning For Fast Optimization of Computation GraphsMay 07 2019May 30 2019We present a deep reinforcement learning approach to optimizing the execution cost of computation graphs in a static compiler. The key idea is to combine a neural network policy with a genetic algorithm, the Biased Random-Key Genetic Algorithm (BRKGA). ... More

Compositional Imitation Learning: Explaining and executing one task at a timeDec 04 2018We introduce a framework for Compositional Imitation Learning and Execution (CompILE) of hierarchically-structured behavior. CompILE learns reusable, variable-length segments of behavior from demonstration data using a novel unsupervised, fully-differentiable ... More

CompILE: Compositional Imitation Learning and ExecutionDec 04 2018May 14 2019We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence ... More

Polarization evolution dynamics of dissipative soliton fiber laserNov 19 2018Dec 23 2018Dissipative solitons are localized solutions in non-integrable and non-conservative nonlinear system, due to a balance of nonlinearity, dispersion, filtering, and loss/gain. Different from conventional soliton, they exhibit extremely complex and striking ... More

Coherent optical modulation of partially mode-locked fiber laser based on coherent population oscillation in reduced oxide grapheneFeb 14 2019Optical control of graphene-based photonic devices and systems has been under extensive explorations, nevertheless, the requirement of high power pump laser due to incoherent modulation makes those schemes low efficient. Here, we demonstrate coherent ... More

Learning model-based planning from scratchJul 19 2017Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to construct a ... More

Clustering via Content-Augmented Stochastic BlockmodelsMay 25 2015Much of the data being created on the web contains interactions between users and items. Stochastic blockmodels, and other methods for community detection and clustering of bipartite graphs, can infer latent user communities and latent item clusters from ... More

XPS studies of nitrogen doping niobium used for accelerator applicationsApr 20 2018Nitrogen doping study on niobium (Nb) samples used for the fabrication of superconducting radio frequency (SRF) cavities was carried out. The samples' surface treatment was attempted to replicate that of the Nb SRF cavities, which includes heavy electropolishing ... More

Accurate color imaging of pathology slides using holography and absorbance spectrum estimation of histochemical stainsSep 08 2018Holographic microscopy presents challenges for color reproduction due to the usage of narrow-band illumination sources, which especially impacts the imaging of stained pathology slides for clinical diagnoses. Here, an accurate color holographic microscopy ... More

Smith-Purcell Radiation from Low-Energy ElectronsOct 15 2017Recent advances in the fabrication of nanostructures and nanoscale features in metasurfaces offer a new prospect for generating visible, light emission from low energy electrons. In this paper, we present the experimental observation of visible light ... More

Areas of triangles and Beck's theorem in planes over finite fieldsMay 01 2012It is shown that any subset $E$ of a plane over a finite field $\F_q$, of cardinality $|E|>q$ determines not less than $\frac{q-1}{2}$ distinct areas of triangles, moreover once can find such triangles sharing a common base. It is also shown that if $|E|\geq ... More

Observation of the chiral anomaly induced negative magneto-resistance in 3D Weyl semi-metal TaAsMar 04 2015Weyl semi-metal is the three dimensional analog of graphene. According to the quantum field theory, the appearance of Weyl points near the Fermi level will cause novel transport phenomena related to chiral anomaly. In the present paper, we report the ... More

When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image ClassifiersOct 31 2018This paper addresses detection of a reverse engineering (RE) attack targeting a deep neural network (DNN) image classifier; by querying, RE's aim is to discover the classifier's decision rule. RE can enable test-time evasion attacks, which require knowledge ... More

Adversarial Occlusion-aware Face DetectionSep 15 2017Sep 29 2018Occluded face detection is a challenging detection task due to the large appearance variations incurred by various real-world occlusions. This paper introduces an Adversarial Occlusion-aware Face Detector (AOFD) by simultaneously detecting occluded faces ... More

Imagination-Augmented Agents for Deep Reinforcement LearningJul 19 2017Feb 14 2018We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe ... More

Relational Deep Reinforcement LearningJun 05 2018Jun 28 2018We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning. It uses self-attention to ... More

Pose Invariant Embedding for Deep Person Re-identificationJan 26 2017Pedestrian misalignment, which mainly arises from detector errors and pose variations, is a critical problem for a robust person re-identification (re-ID) system. With bad alignment, the background noise will significantly compromise the feature learning ... More

Variance Reduction for Matrix GamesJul 03 2019We present a randomized primal-dual algorithm that solves the problem $\min_{x} \max_{y} y^\top A x$ to additive error $\epsilon$ in time $\mathrm{nnz}(A) + \sqrt{\mathrm{nnz}(A)n}/\epsilon$, for matrix $A$ with larger dimension $n$ and $\mathrm{nnz}(A)$ ... More

High density array of epitaxial BiFeO3 nanodots with robust and reversibly switchable topological domain statesMar 30 2017The exotic topological domains in ferroelectrics and multiferroics have attracted extensive interest in recent years due to their novel functionalities and potential applications in nanoelectronic devices. One of the key challenges for such applications ... More

3D Face Synthesis Driven by Personality ImpressionSep 27 2018Synthesizing 3D faces that give certain personality impressions is commonly needed in computer games, animations, and virtual world applications for producing realistic virtual characters. In this paper, we propose a novel approach to synthesize 3D faces ... More

A Fast Proximal Point Method for Computing Wasserstein DistanceFeb 12 2018Jun 14 2018Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations ... More

Analytical description of high-aperture STED resolution with 0-2$π$ vortex phase modulationFeb 07 2013Stimulated emission depletion (STED) can achieve optical super-resolution, with the optical diffraction limit broken by the suppression on the periphery of the fluorescent focal spot. Previously, it is generally experimentally accepted that there exists ... More

On Scalable and Efficient Computation of Large Scale Optimal TransportMay 01 2019Jun 24 2019Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses. To address the scalability issue, we propose an implicit generative learning-based framework called SPOT (Scalable ... More

Meta Learning with Relational Information for Short SequencesSep 04 2019This paper proposes a new meta-learning method -- named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network. Specifically, ... More

"Why Should You Trust My Explanation?" Understanding Uncertainty in LIME ExplanationsApr 29 2019Jun 04 2019Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain significant uncertainty ... More

A geometry-inspired decision-based attackMar 26 2019Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by ... More

Deriving Machine Attention from Human RationalesAug 28 2018Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated rationales and ... More

Few-shot Text Classification with Distributional SignaturesAug 16 2019In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this approach to text ... More

On Scalable and Efficient Computation of Large Scale Optimal TransportMay 01 2019Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses. To address the scalability issue, we propose an implicit generative learning-based framework called SPOT (Scalable ... More

On Scalable and Efficient Computation of Large Scale Optimal TransportMay 01 2019May 14 2019Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses. To address the scalability issue, we propose an implicit generative learning-based framework called SPOT (Scalable ... More

A Fast Proximal Point Method for Computing Exact Wasserstein DistanceFeb 12 2018Jun 24 2019Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations ... More

Chow Motive of Fulton-MacPherson configuration spaces and wonderful compactificationsNov 15 2006Jan 01 2009We study the Chow groups and the Chow motives of the wonderful compactifications $Y_{\mathcal{G}}$ of arrangements of subvarieties. We prove a natural decomposition of the Chow motive of $Y_\mathcal{G}$, in particular of the Fulton-MacPherson configuration ... More

Hyperscaling Violating Solutions in Generalised EMD TheoryAug 10 2016Sep 01 2016This short note is devoted to deriving scaling but hyperscaling violating solutions in a generalised Einstein-Maxwell-Dilaton theory with an arbitrary number of scalars and vectors. We obtain analytic solutions in some special case and discuss the physical ... More

Phase transition for accessibility percolation on hypercubesFeb 26 2015Jun 02 2017In this paper, we consider accessibility percolation on hypercubes, i.e., we place i.i.d. uniform [0,1] random variables on vertices of a hypercube, and study whether there is a path connecting two vertices such that the values of these random variables ... More

Relational inductive biases, deep learning, and graph networksJun 04 2018Oct 17 2018Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural ... More

Phase transition for accessibility percolation on hypercubesFeb 26 2015In this paper, we consider accessibility percolation on hypercubes, i.e., we place i.i.d.\ uniform random variables on vertices of a hypercube, and study whether there is a path (possibly with back steps) connecting two vertices such that the values of ... More

Wonderful compactification of an arrangement of subvarietiesNov 14 2006Jan 01 2009We define the wonderful compactification of an arrangement of subvarieties. Given a complex nonsingular algebraic variety $Y$ and certain collection $\mathcal{G}$ of subvarieties of $Y$, the wonderful compactification $Y_\mathcal{G}$ can be constructed ... More

Why should you trust my interpretation? Understanding uncertainty in LIME predictionsApr 29 2019Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain significant uncertainty ... More

ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient SegmentationApr 20 2018Feb 12 2019Salient segmentation aims to segment out attention-grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and benefits from ... More

Query-Conditioned Three-Player Adversarial Network for Video SummarizationJul 17 2018Video summarization plays an important role in video understanding by selecting key frames/shots. Traditionally, it aims to find the most representative and diverse contents in a video as short summaries. Recently, a more generalized task, query-conditioned ... More

An Efficient Two-Port Electron Beam Splitter via Quantum Interaction-Free MeasurementAug 09 2018Aug 14 2018Semi-transparent mirrors are standard elements in light optics for splitting light beams or creating two versions of the same image. Such mirrors do not exist in electron optics, although they could be beneficial in existing techniques such as electron ... More

Hyperspectral Light Field Stereo MatchingSep 04 2017In this paper, we describe how scene depth can be extracted using a hyperspectral light field capture (H-LF) system. Our H-LF system consists of a 5 x 6 array of cameras, with each camera sampling a different narrow band in the visible spectrum. There ... More

Reconstruction-Aware Imaging System Ranking by use of a Sparsity-Driven Numerical Observer Enabled by Variational Bayesian InferenceMay 14 2019It is widely accepted that optimization of imaging system performance should be guided by task-based measures of image quality (IQ). It has been advocated that imaging hardware or data-acquisition designs should be optimized by use of an ideal observer ... More

Detection based Defense against Adversarial Examples from the Steganalysis Point of ViewJun 21 2018Dec 24 2018Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically misleading the DNNs. Moreover, adversarial ... More

Active Image Synthesis for Efficient LabelingFeb 05 2019Sep 01 2019The great success achieved by deep neural networks attracts increasing attention from the manufacturing and healthcare communities. However, the limited availability of data and high costs of data collection are the major challenges for the applications ... More

Rethinking Knowledge Graph Propagation for Zero-Shot LearningMay 29 2018May 31 2018The potential of graph convolutional neural networks for the task of zero-shot learning has been demonstrated recently. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization ... More

Scheduling Distributed Resources in Heterogeneous Private CloudsMay 17 2017Dec 30 2018We first consider the static problem of allocating resources to ( i.e. , scheduling) multiple distributed application framework s, possibly with different priorities and server preferences , in a private cloud with heterogeneous servers. Several fai r ... More

Rethinking Knowledge Graph Propagation for Zero-Shot LearningMay 29 2018Mar 27 2019Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes ... More

Anomalous Hall Effect and Spin Fluctuations in Ionic Liquid Gated SrCoO$_3$ Thin FilmsJul 28 2018The recent realization of epitaxial SrCoO$_3$ thin films has triggered a renewed interest in their electronic, magnetic, and ionic properties. Here we uncover several unusual magneto-transport properties of this compound, suggesting that it hosts persistent ... More

DTR-GAN: Dilated Temporal Relational Adversarial Network for Video SummarizationApr 30 2018The large amount of videos popping up every day, make it is more and more critical that key information within videos can be extracted and understood in a very short time. Video summarization, the task of finding the smallest subset of frames, which still ... More

Unsupervised Object-Level Video Summarization with Online Motion Auto-EncoderJan 02 2018Aug 11 2018Unsupervised video summarization plays an important role on digesting, browsing, and searching the ever-growing videos every day, and the underlying fine-grained semantic and motion information (i.e., objects of interest and their key motions) in online ... More

Semantic-driven Generation of Hyperlapse from $360^\circ$ VideoMar 31 2017Oct 10 2017We present a system for converting a fully panoramic ($360^\circ$) video into a normal field-of-view (NFOV) hyperlapse for an optimal viewing experience. Our system exploits visual saliency and semantics to non-uniformly sample in space and time for generating ... More

IDK Cascades: Fast Deep Learning by Learning not to OverthinkJun 03 2017Jun 27 2018Advances in deep learning have led to substantial increases in prediction accuracy but have been accompanied by increases in the cost of rendering predictions. We conjecture that fora majority of real-world inputs, the recent advances in deep learning ... More

AVP: Physics-informed Data Generation for Small-data LearningFeb 05 2019Deep neural networks have achieved great success in multiple learning problems, and attracted increasing attention from the medicine community. In reality, however, the limited availability and high costs of medical data is a major challenge of applying ... More

Out-of-Distribution Detection Using Neural Rendering Generative ModelsJul 10 2019Out-of-distribution (OoD) detection is a natural downstream task for deep generative models, due to their ability to learn the input probability distribution. There are mainly two classes of approaches for OoD detection using deep generative models, viz., ... More

Implicit Asymptotic Preserving Method for Linear Transport EquationsFeb 01 2016The computation of the radiative transfer equation is expensive mainly due to two stiff terms: the transport term and the collision operator. The stiffness in the former comes from the fact that particles (such as photons) travels at the speed of light, ... More

Towards Label Imbalance in Multi-label Classification with Many LabelsApr 05 2016In multi-label classification, an instance may be associated with a set of labels simultaneously. Recently, the research on multi-label classification has largely shifted its focus to the other end of the spectrum where the number of labels is assumed ... More

Network analysis of the state space of chaotic map in digital domainOct 28 2014Nov 04 2014Complex dynamics of chaotic maps under an infinite-precision mathematical framework have been well known. The case in a finite-precision computer remains to be further explored. Previous work treated a digital chaotic map as a black box and gave different ... More

Novel Algorithm for Sparse Solutions to Linear Inverse Problems with Multiple MeasurementsMay 20 2009In this report, a novel efficient algorithm for recovery of jointly sparse signals (sparse matrix) from multiple incomplete measurements has been presented, in particular, the NESTA-based MMV optimization method. In a nutshell, the jointly sparse recovery ... More

Beat the Rayleigh limit: OAM based super-resolution diffraction tomographyJun 27 2013This letter is the first to report that a super-resolution imaging beyond the Rayleigh limit can be achieved by using classical diffraction tomography (DT) extended with orbital angular momentum (OAM), termed as OAM based diffraction tomography (OAM-DT). ... More

The neighbor-scattering number can be computed in polynomial time for interval graphsMar 17 2006Neighbor-scattering number is a useful measure for graph vulnerability. For some special kinds of graphs, explicit formulas are given for this number. However, for general graphs it is shown that to compute this number is NP-complete. In this paper, we ... More

Effects of alpha particles on the angular momentum loss from the SunJun 07 2006The classic Weber-Davis model of the solar wind is reconsidered by incorporating alpha particles and by allowing the solar wind to flow out of the equatorial plane in an axisymmetrical configuration. In the ion momentum equations of the solar wind, the ... More

Chemical distances for percolation of planar Gaussian free fields and critical random walk loop soupsMay 14 2016Aug 29 2016We initiate the study on chemical distances of percolation clusters for level sets of two-dimensional discrete Gaussian free fields as well as loop clusters generated by two-dimensional random walk loop soups. One of our results states that the chemical ... More

A New Unified Theory of Electromagnetic and Gravitational InteractionsNov 04 2015Mar 30 2016In this paper we present a new unified theory of electromagnetic and gravitational interactions. By considering a four-dimensional spacetime as a hypersurface embedded in a five-dimensional bulk spacetime, we derive the complete set of field equations ... More

Global existence of weak solutions for quantum MHD equationsMay 07 2018In this paper, we consider the quantum MHD equations with both the viscosity coefficient and the magnetic diffusion coefficient are depend on the density. we prove the global existence of weak solutions and perform the lower planck limit in a 3-dimensional ... More

Optimal Deployment of Drone Base Stations for Cellular Communication by Network-based LocalizationSep 19 2018Drone base stations can assist cellular networks in a variety of scenarios. To serve the maximum number of users in an area without apriori user distribution information, we proposed a two-stage algorithm to find the optimal deployment of drone base stations. ... More

Polynomial invariants of degree 4 for even-$n$ qubits and their applications in entanglement classificationAug 11 2013We develop a simple method for constructing polynomial invariants of degree 4 for even-$n$ qubits and give explicit expressions for these polynomial invariants. We demonstrate the invariance of the polynomials under stochastic local operations and classical ... More