arXiv subjects

Han Liu

Publications and source records attributed to Han Liu.

At least 289 records · Page 16Linked to original sources

arXiv2020

Finite-Sample Analysis For Decentralized Batch Multi-Agent Reinforcement Learning With Networked Agents

Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents. Specifically, we consider two decentralized MARL settings, where teams of agents are connected by time-varying communication networks, and either collaborate or compete in a zero-sum game setting, without any central controller. These settings cover many conventional MARL settings in the literature. For both settings, we develop batch MARL algorithms that can be implemented in a decentralized fashion, and quantify the finite-sample errors of the estimated action-value functions. Our error analysis captures how the function class, the number of samples within each iteration, and the number of iterations determine the statistical accuracy of the proposed algorithms. Our results, compared to the finite-sample bounds for single-agent RL, involve additional error terms caused by decentralized computation, which is inherent in our decentralized MARL setting. This work appears to be the first finite-sample analysis for batch MARL, a step towards rigorous theoretical understanding of general MARL algorithms in the finite-sample regime.

cs.LG↗

arXiv2020

Morphology Matters: A Multilingual Language Modeling Analysis

Prior studies in multilingual language modeling (e.g., Cotterell et al., 2018; Mielke et al., 2019) disagree on whether or not inflectional morphology makes languages harder to model. We attempt to resolve the disagreement and extend those studies. We compile a larger corpus of 145 Bible translations in 92 languages and a larger number of typological features. We fill in missing typological data for several languages and consider corpus-based measures of morphological complexity in addition to expert-produced typological features. We find that several morphological measures are significantly associated with higher surprisal when LSTM models are trained with BPE-segmented data. We also investigate linguistically-motivated subword segmentation strategies like Morfessor and Finite-State Transducers (FSTs) and find that these segmentation strategies yield better performance and reduce the impact of a language's morphology on language modeling.

cs.CL↗

arXiv2020

FAME: 3D Shape Generation via Functionality-Aware Model Evolution

We introduce a modeling tool which can evolve a set of 3D objects in a functionality-aware manner. Our goal is for the evolution to generate large and diverse sets of plausible 3D objects for data augmentation, constrained modeling, as well as open-ended exploration to possibly inspire new designs. Starting with an initial population of 3D objects belonging to one or more functional categories, we evolve the shapes through part recombination to produce generations of hybrids or crossbreeds between parents from the heterogeneous shape collection. Evolutionary selection of offsprings is guided both by a functional plausibility score derived from functionality analysis of shapes in the initial population and user preference, as in a design gallery. Since cross-category hybridization may result in offsprings not belonging to any of the known functional categories, we develop a means for functionality partial matching to evaluate functional plausibility on partial shapes. We show a variety of plausible hybrid shapes generated by our functionality-aware model evolution, which can complement existing datasets as training data and boost the performance of contemporary data-driven segmentation schemes, especially in challenging cases. Our tool supports constrained modeling, allowing users to restrict or steer the model evolution with functionality labels. At the same time, unexpected yet functional object prototypes can emerge during open-ended exploration owing to structure breaking when evolving a heterogeneous collection.

cs.GR↗

arXiv2020

Uncertainty Estimation in Medical Image Localization: Towards Robust Anterior Thalamus Targeting for Deep Brain Stimulation

Atlas-based methods are the standard approaches for automatic targeting of the Anterior Nucleus of the Thalamus (ANT) for Deep Brain Stimulation (DBS), but these are known to lack robustness when anatomic differences between atlases and subjects are large. To improve the localization robustness, we propose a novel two-stage deep learning (DL) framework, where the first stage identifies and crops the thalamus regions from the whole brain MRI and the second stage performs per-voxel regression on the cropped volume to localize the targets at the finest resolution scale. To address the issue of data scarcity, we train the models with the pseudo labels which are created based on the available labeled data using multi-atlas registration. To assess the performance of the proposed framework, we validate two sampling-based uncertainty estimation techniques namely Monte Carlo Dropout (MCDO) and Test-Time Augmentation (TTA) on the second-stage localization network. Moreover, we propose a novel uncertainty estimation metric called maximum activation dispersion (MAD) to estimate the image-wise uncertainty for localization tasks. Our results show that the proposed method achieved more robust localization performance than the traditional multi-atlas method and TTA could further improve the robustness. Moreover, the epistemic and hybrid uncertainty estimated by MAD could be used to detect the unreliable localizations and the magnitude of the uncertainty estimated by MAD could reflect the degree of unreliability for the rejected predictions.

eess.IV↗

arXiv2020

The quantum tunnel effect of photon in one-dimensional photonic crystals

In the paper, we have given the quantum transmissivity, probability density and probability current density of photon in one-dimensional photonic crystals $(AB)^N$ with the quantum theory approach. We find the quantum transmissivity is identical to the classical transmissivity. When the incident angle $θ$ and periodic number $N$ change the probability density and probability current density are approximate periodic change, and their amplitude are increased with the incident angles $θ$ and periodic number $N$ increasing. Otherwise, we find when the frequency of incident photon is corresponding to transmissivity $T=1$, the amplitude of the probability density is the largest. When the frequency of incident photon is corresponding to transmissivity $T=0$, the amplitude of the probability density attenuate rapidly to zero, it indicates that there is the quantum tunnel effect of photon in photonic crystals.

quant-ph↗

arXiv2020

Label-Wise Document Pre-Training for Multi-Label Text Classification

A major challenge of multi-label text classification (MLTC) is to stimulatingly exploit possible label differences and label correlations. In this paper, we tackle this challenge by developing Label-Wise Pre-Training (LW-PT) method to get a document representation with label-aware information. The basic idea is that, a multi-label document can be represented as a combination of multiple label-wise representations, and that, correlated labels always cooccur in the same or similar documents. LW-PT implements this idea by constructing label-wise document classification tasks and trains label-wise document encoders. Finally, the pre-trained label-wise encoder is fine-tuned with the downstream MLTC task. Extensive experimental results validate that the proposed method has significant advantages over the previous state-of-the-art models and is able to discover reasonable label relationship. The code is released to facilitate other researchers.

cs.CL↗

arXiv2020

Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python

We describe a new library named picasso, which implements a unified framework of pathwise coordinate optimization for a variety of sparse learning problems (e.g., sparse linear regression, sparse logistic regression, sparse Poisson regression and scaled sparse linear regression) combined with efficient active set selection strategies. Besides, the library allows users to choose different sparsity-inducing regularizers, including the convex $\ell_1$, nonconvex MCP and SCAD regularizers. The library is coded in C++ and has user-friendly R and Python wrappers. Numerical experiments demonstrate that picasso can scale up to large problems efficiently.

stat.ML↗

arXiv2020

The flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R

This paper describes an R package named flare, which implements a family of new high dimensional regression methods (LAD Lasso, SQRT Lasso, $\ell_q$ Lasso, and Dantzig selector) and their extensions to sparse precision matrix estimation (TIGER and CLIME). These methods exploit different nonsmooth loss functions to gain modeling flexibility, estimation robustness, and tuning insensitiveness. The developed solver is based on the alternating direction method of multipliers (ADMM). The package flare is coded in double precision C, and called from R by a user-friendly interface. The memory usage is optimized by using the sparse matrix output. The experiments show that flare is efficient and can scale up to large problems.

stat.ML↗

arXiv2020

The huge Package for High-dimensional Undirected Graph Estimation in R

We describe an R package named huge which provides easy-to-use functions for estimating high dimensional undirected graphs from data. This package implements recent results in the literature, including Friedman et al. (2007), Liu et al. (2009, 2012) and Liu et al. (2010). Compared with the existing graph estimation package glasso, the huge package provides extra features: (1) instead of using Fortan, it is written in C, which makes the code more portable and easier to modify; (2) besides fitting Gaussian graphical models, it also provides functions for fitting high dimensional semiparametric Gaussian copula models; (3) more functions like data-dependent model selection, data generation and graph visualization; (4) a minor convergence problem of the graphical lasso algorithm is corrected; (5) the package allows the user to apply both lossless and lossy screening rules to scale up large-scale problems, making a tradeoff between computational and statistical efficiency.

stat.ML↗

arXiv2020

Joint measurement of time-frequency entanglement via sum frequency generation

We propose, analyze, and evaluate a technique for the joint measurement of time-frequency entanglement between two photons. In particular, we show that the frequency sum and time difference of two photons could be simultaneously measured through the sum-frequency generation process, without measuring the time or frequency of each individual photon. We demonstrate the usefulness of this technique by using it to design a time-frequency entanglement based continuous variable superdense coding and a quantum illumination protocol. Performance analysis of these two protocols suggests that the joint measurement of strong time-frequency entanglement of non-classical photon pairs can significantly enhance the performance of joint-measurement based quantum communication and metrology protocols.

quant-ph↗

arXiv2020

Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network

In this paper, we explore the slot tagging with only a few labeled support sentences (a.k.a. few-shot). Few-shot slot tagging faces a unique challenge compared to the other few-shot classification problems as it calls for modeling the dependencies between labels. But it is hard to apply previously learned label dependencies to an unseen domain, due to the discrepancy of label sets. To tackle this, we introduce a collapsed dependency transfer mechanism into the conditional random field (CRF) to transfer abstract label dependency patterns as transition scores. In the few-shot setting, the emission score of CRF can be calculated as a word's similarity to the representation of each label. To calculate such similarity, we propose a Label-enhanced Task-Adaptive Projection Network (L-TapNet) based on the state-of-the-art few-shot classification model -- TapNet, by leveraging label name semantics in representing labels. Experimental results show that our model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.

cs.CL↗

arXiv2020

A Deep Learning based Wearable Healthcare IoT Device for AI-enabled Hearing Assistance Automation

With the recent booming of artificial intelligence (AI), particularly deep learning techniques, digital healthcare is one of the prevalent areas that could gain benefits from AI-enabled functionality. This research presents a novel AI-enabled Internet of Things (IoT) device operating from the ESP-8266 platform capable of assisting those who suffer from impairment of hearing or deafness to communicate with others in conversations. In the proposed solution, a server application is created that leverages Google's online speech recognition service to convert the received conversations into texts, then deployed to a micro-display attached to the glasses to display the conversation contents to deaf people, to enable and assist conversation as normal with the general population. Furthermore, in order to raise alert of traffic or dangerous scenarios, an 'urban-emergency' classifier is developed using a deep learning model, Inception-v4, with transfer learning to detect/recognize alerting/alarming sounds, such as a horn sound or a fire alarm, with texts generated to alert the prospective user. The training of Inception-v4 was carried out on a consumer desktop PC and then implemented into the AI based IoT application. The empirical results indicate that the developed prototype system achieves an accuracy rate of 92% for sound recognition and classification with real-time performance.

cs.HC↗

arXiv2020

Neural Polysynthetic Language Modelling

Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segmentation are often used when either of those assumptions do not hold, particularly in the case of synthetic languages like Spanish or Russian that have more inflection than English. In the literature, languages like Finnish or Turkish are held up as extreme examples of complexity that challenge common modelling assumptions. Yet, when considering all of the world's languages, Finnish and Turkish are closer to the average case. When we consider polysynthetic languages (those at the extreme of morphological complexity), approaches like stemming, lemmatization, or subword modelling may not suffice. These languages have very high numbers of hapax legomena, showing the need for appropriate morphological handling of words, without which it is not possible for a model to capture enough word statistics. We examine the current state-of-the-art in language modelling, machine translation, and text prediction for four polysynthetic languages: Guaraní, St. Lawrence Island Yupik, Central Alaskan Yupik, and Inuktitut. We then propose a novel framework for language modelling that combines knowledge representations from finite-state morphological analyzers with Tensor Product Representations in order to enable neural language models capable of handling the full range of typologically variant languages.

cs.CL↗

arXiv2020

Enhancing classical target detection performance using nonclassical Light

In this article, we demonstrate theoretically and experimentally how one can exploit correlations generated in monolithic semiconductor quantum light sources to enhance the performance of optical target detection. A prototype target detection protocol, the quantum time-correlation (QTC) detection protocol, with spontaneous parametric down-converted photon-pair sources, is discussed. The QTC protocol only requires time-resolved photon-counting detection, which is phase-insensitive and therefore suitable for optical target detection. As a comparison to the QTC detection protocol, we also consider a classical phase-insensitive target detection protocol based on intensity detection. We formulated the target detection problem as a probe light transmission estimation problem, and we quantify the target detection performance with the Fisher information criterion and the receiver operation characteristic analysis. Unlike classical target detection and ranging protocols, the probe photons in our QTC detection protocol are completely indistinguishable from the background noise and therefore useful for covert ranging applications. Finally, our technological platform is highly scalable and tunable and thus amenable to large scale integration necessary for practical applications.

physics.optics↗

arXiv2020

Non-classical Semiconductor Photon Sources Enhancing the Performance of Classical Target Detection Systems

We demonstrate and analyze how deploying non-classical intensity correlations obtained from a monolithic semiconductor quantum photon source can enhance classical target detection systems. This is demonstrated by examining the advantages offered by the utilization of the non-classical correlations in a correlation based target detection protocol. We experimentally demonstrate that under the same condition, the target contrast obtained from the protocol when non-classical correlations are utilized exhibits an improvement of up to 17.79dB over the best classical intensity correlation-based target detection protocol, under 29.69dB channel loss and excess noise 13.40dB stronger than the probe signal. We also assessed how the strong frequency correlations within the non-classical photon pairs can be used to further enhance this protocol.

physics.optics↗

arXiv2020

Target Detection aided by Quantum Temporal Correlations: Theoretical Analysis and Experimental Validation

The detection of objects in the presence of significant background noise is a problem of fundamental interest in sensing. In this work, we theoretically analyze a prototype target detection protocol, the quantum temporal correlation (QTC) detection protocol, which is implemented in this work utilizing spontaneous parametric down-converted photon-pair sources. The QTC detection protocol only requires time-resolved photon-counting detection, which is phase-insensitive and therefore suitable for optical target detection. As a comparison to the QTC detection protocol, we also consider a classical phase-insensitive target detection protocol based on intensity detection that is practical in the optical regime. We formulated the target detection problem as a total probe photon transmission estimation problem and obtain an analytical expression of the receiver operating characteristic (ROC) curves. We carry out experiments using a semiconductor waveguide source, which we developed and previously reported. The experimental results agree very well with the theoretical prediction. In particular, we find that in a high-level environment noise and loss, the QTC detection protocol can achieve performance comparable to that of the classical protocol (that is practical in the optical regime) but with $\simeq 57$ times lower detection time in terms of ROC curve metric. The performance of the QTC detection protocol experiment setup could be further improved with a higher transmission of the reference photon and better detector time uncertainty. Furthermore, the probe photons in the QTC detection protocol are completely indistinguishable from the background noise and therefore useful for covert ranging applications. Finally, our technological platform is highly scalable as well as tunable and thus amenable to large scale integration, which is necessary for practical applications.

physics.optics↗

arXiv2020

Enhancing LIDAR performance metrics using continuous-wave photon-pair sources

In order to enhance LIDAR performance metrics such as target detection sensitivity, noise resilience and ranging accuracy, we exploit the strong temporal correlation within the photon pairs generated in continuous-wave pumped semiconductor waveguides. The enhancement attained through the use of such non-classical sources is measured and compared to a corresponding target detection scheme based on simple photon-counting detection. The performances of both schemes are quantified by the estimation uncertainty and Fisher information of the probe photon transmission, which is a widely adopted sensing figure of merit. The target detection experiments are conducted with high probe channel loss ($\simeq 1-5\times10^{-5}$) and formidable environment noise up to 36 dB stronger than the detected probe power of $1.64\times 10^{-5}$ pW. The experimental result shows significant advantages offered by the enhanced scheme with up to 26.3 dB higher performance in terms of estimation uncertainty, which is equivalent to a reduction of target detection time by a factor of 430 or 146 (21.6 dB) times more resilience to noise. We also experimentally demonstrated ranging with these non-classical photon pairs generated with continuous-wave pump in the presence of strong noise and loss, achieving $\approx$5 cm distance resolution that is limited by the temporal resolution of the detectors.

physics.optics↗

arXiv2020

SDFN: Segmentation-based Deep Fusion Network for Thoracic Disease Classification in Chest X-ray Images

This study aims to automatically diagnose thoracic diseases depicted on the chest x-ray (CXR) images using deep convolutional neural networks. The existing methods generally used the entire CXR images for training purposes, but this strategy may suffer from two drawbacks. First, potential misalignment or the existence of irrelevant objects in the entire CXR images may cause unnecessary noise and thus limit the network performance. Second, the relatively low image resolution caused by the resizing operation, which is a common preprocessing procedure for training neural networks, may lead to the loss of image details, making it difficult to detect pathologies with small lesion regions. To address these issues, we present a novel method termed as segmentation-based deep fusion network (SDFN), which leverages the domain knowledge and the higherresolution information of local lung regions. Specifically, the local lung regions were identified and cropped by the Lung Region Generator (LRG). Two CNN-based classification models were then used as feature extractors to obtain the discriminative features of the entire CXR images and the cropped lung region images. Lastly, the obtained features were fused by the feature fusion module for disease classification. Evaluated by the NIH benchmark split on the Chest X-ray 14 Dataset, our experimental result demonstrated that the developed method achieved more accurate disease classification compared with the available approaches via the receiver operating characteristic (ROC) analyses. It was also found that the SDFN could localize the lesion regions more precisely as compared to the traditional method.

cs.CV↗