arXiv subjects

Lei Li

Publications and source records attributed to Lei Li.

At least 721 records · Page 40Linked to original sources

arXiv2020

End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds

In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.

cs.CV↗

arXiv2020

A random-batch Monte Carlo method for many-body systems with singular kernels

We propose a fast potential splitting Markov Chain Monte Carlo method which costs $O(1)$ time each step for sampling from equilibrium distributions (Gibbs measures) corresponding to particle systems with singular interacting kernels. We decompose the interacting potential into two parts, one is of long range but is smooth, and the other one is of short range but may be singular. To displace a particle, we first evolve a selected particle using the stochastic differential equation (SDE) under the smooth part with the idea of random batches, as commonly used in stochastic gradient Langevin dynamics. Then, we use the short range part to do a Metropolis rejection. Different from the classical Langevin dynamics, we only run the SDE dynamics with random batch for a short duration of time so that the cost in the first step is $O(p)$, where $p$ is the batch size. The cost of the rejection step is $O(1)$ since the interaction used is of short range. We justify the proposed random-batch Monte Carlo method, which combines the random batch and splitting strategies, both in theory and with numerical experiments. While giving comparable results for typical examples of the Dyson Brownian motion and Lennard-Jones fluids, our method can save more time when compared to the classical Metropolis-Hastings algorithm.

physics.comp-ph↗

arXiv2020

A consensus-based global optimization method for high dimensional machine learning problems

We improve recently introduced consensus-based optimization method, proposed in [R. Pinnau, C. Totzeck, O. Tse and S. Martin, Math. Models Methods Appl. Sci., 27(01):183--204, 2017], which is a gradient-free optimization method for general non-convex functions. We first replace the isotropic geometric Brownian motion by the component-wise one, thus removing the dimensionality dependence of the drift rate, making the method more competitive for high dimensional optimization problems. Secondly, we utilize the random mini-batch ideas to reduce the computational cost of calculating the weighted average which the individual particles tend to relax toward. For its mean-field limit--a nonlinear Fokker-Planck equation--we prove, in both time continuous and semi-discrete settings, that the convergence of the method, which is exponential in time, is guaranteed with parameter constraints {\it independent} of the dimensionality. We also conduct numerical tests to high dimensional problems to check the success rate of the method.

math.OC↗

arXiv2020

SPAN: A Stochastic Projected Approximate Newton Method

Second-order optimization methods have desirable convergence properties. However, the exact Newton method requires expensive computation for the Hessian and its inverse. In this paper, we propose SPAN, a novel approximate and fast Newton method. SPAN computes the inverse of the Hessian matrix via low-rank approximation and stochastic Hessian-vector products. Our experiments on multiple benchmark datasets demonstrate that SPAN outperforms existing first-order and second-order optimization methods in terms of the convergence wall-clock time. Furthermore, we provide a theoretical analysis of the per-iteration complexity, the approximation error, and the convergence rate. Both the theoretical analysis and experimental results show that our proposed method achieves a better trade-off between the convergence rate and the per-iteration efficiency.

math.OC↗

arXiv2020

Variational Template Machine for Data-to-Text Generation

How to generate descriptions from structured data organized in tables? Existing approaches using neural encoder-decoder models often suffer from lacking diversity. We claim that an open set of templates is crucial for enriching the phrase constructions and realizing varied generations. Learning such templates is prohibitive since it often requires a large paired corpus, which is seldom available. This paper explores the problem of automatically learning reusable "templates" from paired and non-paired data. We propose the variational template machine (VTM), a novel method to generate text descriptions from data tables. Our contributions include: a) we carefully devise a specific model architecture and losses to explicitly disentangle text template and semantic content information, in the latent spaces, and b)we utilize both small parallel data and large raw text without aligned tables to enrich the template learning. Experiments on datasets from a variety of different domains show that VTM is able to generate more diversely while keeping a good fluency and quality.

cs.CL↗

arXiv2020

In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes

Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently. Despite these models provide high ROUGE scores, they are limited to generate comprehensive summaries with a high level of abstraction due to its degenerated attention distribution. We introduce Diverse Convolutional Seq2Seq Model(DivCNN Seq2Seq) using Determinantal Point Processes methods(Micro DPPs and Macro DPPs) to produce attention distribution considering both quality and diversity. Without breaking the end to end architecture, DivCNN Seq2Seq achieves a higher level of comprehensiveness compared to vanilla models and strong baselines. All the reproducible codes and datasets are available online.

cs.CL↗

arXiv2019

Task-Aware Monocular Depth Estimation for 3D Object Detection

Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions ("things and stuff") in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.

cs.CV↗

arXiv2019

Period doubling of multiple dissipative-soliton-resonance pulses in a fiber laser

We report on the experimental observation of period doubling of multiple dissipative-soliton-resonance (DSR) pulses in an all-normal-dispersion fiber laser based on a nonlinear amplifying loop mirror. By increasing the pump power, in addition to the typically linearly pulse broadening under fixed pulse peak power, the jump from a single DSR pulse to multiple DSR pulses was observed. During this process, the period doubling appears, that is, the DSR pulses can exhibit the characteristics of period doubling in a multi-pulse state. The typical DSR performance of linearly pulse duration change versus pump power varying can be maintained when the period doubling of multiple DSR pulses appears.

nlin.PS↗

arXiv2019

Importance-Aware Learning for Neural Headline Editing

Many social media news writers are not professionally trained. Therefore, social media platforms have to hire professional editors to adjust amateur headlines to attract more readers. We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers. To train such a neural headline editing model, we collected a dataset which contains articles with original headlines and professionally edited headlines. However, it is expensive to collect a large number of professionally edited headlines. To solve this low-resource problem, we design an encoder-decoder model which leverages large scale pre-trained language models. We further improve the pre-trained model's quality by introducing a headline generation task as an intermediate task before the headline editing task. Also, we propose Self Importance-Aware (SIA) loss to address the different levels of editing in the dataset by down-weighting the importance of easily classified tokens and sentences. With the help of Pre-training, Adaptation, and SIA, the model learns to generate headlines in the professional editor's style. Experimental results show that our method significantly improves the quality of headline editing comparing against previous methods.

cs.CL↗

arXiv2019

Period doubling eigenstates in a fiber laser mode-locked by nonlinear polarization rotation

Due to the weak birefringence of single mode fibers, solitons generated in fiber lasers are indeed vector pulses and exhibit periodic parameter change including polarization evolution even when there is a polarizer inside the cavity. Period doubling eigenstates of solitons generated in a fiber laser mode-locked by the nonlinear polarization rotation, i.e., period doubling of polarization components of the soliton, are numerically explored in detail. We found that, apart from the synchronous evolution between the two polarization components, there exists asynchronous development depending on the detailed operation conditions. In addition, period doubling of one polarization component together with period-one of another polarization component can be achieved. When the period tripling window is obtained, much complexed dynamics on the two polarization components could be observed.

nlin.CD↗

arXiv2019

Period-doubling bifurcation of dissipative-soliton-resonance pulses in a passively mode-locked fiber laser

We report on the experimental observation of period-doubling bifurcation of dissipative-soliton-resonance (DSR) pulses in a fiber laser passively mode-locked by using the nonlinear optical loop mirror. Increasing the pump power of the fiber laser, we show that temporally a stable, uniform DSR pulse train could be transformed into a period-doubling state, exhibiting two sets of pulse parameters between the adjacent cavity roundtrip. It is found that DSR pulses in the period-doubling state could maintain the typical feature of DSR pulse: fixed pulse peak power and linear variation in pulse width with respect to the pump power change. The mechanism for achieving period-doubling of DSR pulses is discussed.

physics.optics↗

arXiv2019

Deep Active Learning for Anchor User Prediction

Predicting pairs of anchor users plays an important role in the cross-network analysis. Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction. To this end, we present a deep active learning model for anchor user prediction (DALAUP for short). However, active learning for anchor user sampling meets the challenges of non-i.i.d. user pair data caused by network structures and the correlation among anchor or non-anchor user pairs. To solve the challenges, DALAUP uses a couple of neural networks with shared-parameter to obtain the vector representations of user pairs, and ensembles three query strategies to select the most informative user pairs for labeling and model training. Experiments on real-world social network data demonstrate that DALAUP outperforms the state-of-the-art approaches.

cs.LG↗

arXiv2019

On the convergence of gradient descent for two layer neural networks

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing works, we investigate the gradient descent method for training two-layer neural networks for approximating some target continuous functions. By making use the generic chaining technique from probability theory, we show that gradient descent can yield an exponential convergence rate, while the width of the neural networks needed is independent of the size of the training data. The result also implies some strong approximation ability of the two-layer neural networks without curse of dimensionality.

math.OC↗

arXiv2019

Kernelized Bayesian Softmax for Text Generation

Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase. Most existing approaches adopt single point embedding for each token. However, a word may have multiple senses according to different context, some of which might be distinct. In this paper, we propose KerBS, a novel approach for learning better embeddings for text generation. KerBS embodies two advantages: (a) it employs a Bayesian composition of embeddings for words with multiple senses; (b) it is adaptive to semantic variances of words and robust to rare sentence context by imposing learned kernels to capture the closeness of words (senses) in the embedding space. Empirical studies show that KerBS significantly boosts the performance of several text generation tasks.

cs.CL↗

arXiv2019

Typical Snapshots Selection for Shortest Path Query in Dynamic Road Networks

Finding the shortest paths in road network is an important query in our life nowadays, and various index structures are constructed to speed up the query answering. However, these indexes can hardly work in real-life scenario because the traffic condition changes dynamically, which makes the pathfinding slower than in the static environment. In order to speed up path query answering in the dynamic road network, we propose a framework to support these indexes. Firstly, we view the dynamic graph as a series of static snapshots. After that, we propose two kinds of methods to select the typical snapshots. The first kind is time-based and it only considers the temporal information. The second category is the graph representation-based, which considers more insights: edge-based that captures the road continuity, and vertex-based that reflects the region traffic fluctuation. Finally, we propose the snapshot matching to find the most similar typical snapshot for the current traffic condition and use its index to answer the query directly. Extensive experiments on real-life road network and traffic conditions validate the effectiveness of our approach.

cs.DB↗

arXiv2019

CNN-based Automatic Detection of Bone Conditions via Diagnostic CT Images for Osteoporosis Screening

Purpose: The purpose is to design a novelty automatic diagnostic method for osteoporosis screening by using the potential capability of convolutional neural network (CNN) in feature representation and extraction, which can be incorporated into the procedure of routine CT diagnostic in physical examination thereby improving the osteoporosis diagnosis and reducing the patient burden. Methods: The proposed convolutional neural network-based method mainly comprises two functional modules to perform automatic detection of bone condition by analyzing the diagnostic CT image. The first functional module aims to locate and segment the ROI of diagnostic CT image, called Mark-Segmentation-Network (MS-Net). The second functional module is used to determine the category of bone condition by the features of ROI, called Bone-Conditions-Classification-Network (BCC-Net). The trained MS-Net can get the mark image of inputted original CT image, thereby obtain the segmentation image. The trained BCC-Net can obtain the probability value of normal bone mass, low bone mass, and osteoporosis by inputting the segmentation image. On the basis of network results, the radiologists can provide preliminary qualitative diagnosis results of bone condition. Results: The proposed MS-Net has an excellent segmentation precision on the shape preservation of different lumbar vertebra. The numerical indicators of segmentation results are greater than 0.998. The proposed BCC-Net was evaluated with 3,024 clinical images and achieved an accuracy of 76.65% and an area under the receiver operating characteristic curve of 0.9167. Conclusions: This study proposed a novel two-step method for automatic detection of bone conditions via diagnostic CT images and it has great potential in clinical applications for osteoporosis screening. The method can potentially reduce the manual burden to radiologists and diagnostic cost to patients.

physics.med-ph↗

arXiv2019

On mean field limit for Brownian particles with Coulomb interaction in 3D

In this paper, we consider the mean field limit of Brownian particles with Coulomb interaction in 3D space. In particular, using a symmetrization technique, we show that the limit measure almost surely is a weak solution to the limiting nonlinear Fokker-Planck equation. By proving that the energy almost surely is bounded by the initial energy, we improve the regularity of the weak solutions. Moreover, by a natural assumption, we establish the weak strong uniqueness principle, which is closely related to the propagation of chaos.

math.AP↗

arXiv2019

Bond Relaxation and Electronic Properties of Two-Dimensional Sb/MoSe2 and Sb/MoTe2 Van der Waals Heterostructures

Van der Waals heterostructures have recently garnered interest for application in high-performance photovoltaic materials. Consequently, understanding the basic electronic characteristics of these heterostructures is important for their utilisation in optoelectronic devices. The electronic structures and bond relaxation of two-dimensional (2D) Sb/transition metal disulfides (TMDs, MoSe2, and MoTe2) van der Waals heterostructures were systematically studied using the bond-charge (BC) correlation and hybrid density functional theory. We found that the Sb/MoSe2 and Sb/MoTe2 heterostructures had indirect band gaps of 0.701 and 0.808 eV, respectively; further, these heterostructures effectively modulated the band gaps of MoSe2 (1.463 eV) and MoTe2 (1.173 eV). The BC correlation revealed four bonding and electronic contributions (electron-holes, antibonding, nonbonding, and bonding states) of the heterostructures. Our results provide an in-depth understanding of the Sb/TMD van der Waals heterojunction, which should be utilised to design 2D metal/semiconductor-based devices.

physics.comp-ph↗