arXiv subjects

Xinyi Li

Publications and source records attributed to Xinyi Li.

157 records · Page 9Linked to original sources

arXiv2020

Characterizing Reading Time on Enterprise Emails

Email is an integral part of people's work and life, enabling them to perform activities such as communicating, searching, managing tasks and storing information. Modern email clients take a step forward and help improve users' productivity by automatically creating reminders, tasks or responses. The act of reading is arguably the only activity that is in common in most -- if not all -- of the interactions that users have with their emails. In this paper, we characterize how users read their enterprise emails, and reveal the various contextual factors that impact reading time. Our approach starts with a reading time analysis based on the reading events from a major email platform, followed by a user study to provide explanations for some discoveries. We identify multiple temporal and user contextual factors that are correlated with reading time. For instance, email reading time is correlated with user devices: on desktop reading time increases through the morning and peaks at noon but on mobile it increases through the evening till midnight. The reading time is also negatively correlated with the screen size. We have established the connection between user status and reading time: users spend more time reading emails when they have fewer meetings and busy hours during the day. In addition, we find that users also reread emails across devices. Among the cross-device reading events, 76% of reread emails are first visited on mobile and then on desktop. Overall, our study is the first to characterize enterprise email reading time on a very large scale. The findings provide insights to develop better metrics and user models for understanding and improving email interactions.

cs.IR↗

arXiv2019

DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News

Stock price prediction is important for value investments in the stock market. In particular, short-term prediction that exploits financial news articles is promising in recent years. In this paper, we propose a novel deep neural network DP-LSTM for stock price prediction, which incorporates the news articles as hidden information and integrates difference news sources through the differential privacy mechanism. First, based on the autoregressive moving average model (ARMA), a sentiment-ARMA is formulated by taking into consideration the information of financial news articles in the model. Then, an LSTM-based deep neural network is designed, which consists of three components: LSTM, VADER model and differential privacy (DP) mechanism. The proposed DP-LSTM scheme can reduce prediction errors and increase the robustness. Extensive experiments on S&P 500 stocks show that (i) the proposed DP-LSTM achieves 0.32% improvement in mean MPA of prediction result, and (ii) for the prediction of the market index S&P 500, we achieve up to 65.79% improvement in MSE.

q-fin.ST↗

arXiv2019

Improving Human Annotation in Single Object Tracking

Human annotation is always considered as ground truth in video object tracking tasks. It is used in both training and evaluation purposes. Thus, ensuring its high quality is an important task for the success of trackers and evaluations between them. In this paper, we give a qualitative and quantitative analysis of the existing human annotations. We show that human annotation tends to be non-smooth and is prone to partial visibility and deformation. We propose a smoothing trajectory strategy with the ability to handle moving scenes. We use a two-step adaptive image alignment algorithm to find the canonical view of the video sequence. We then use different techniques to smooth the trajectories at certain degree. Once we convert back to the original image coordination, we can compare with the human annotation. With the experimental results, we can get more consistent trajectories. At a certain degree, it can also slightly improve the trained model. If go beyond a certain threshold, the smoothing error will start eating up the benefit. Overall, our method could help extrapolate the missing annotation frames or identify and correct human annotation outliers as well as help improve the training data quality.

cs.CV↗

arXiv2019

Percolative properties of Brownian interlacements and its vacant set

In this article we investigate the percolative properties of Brownian interlacements, a model introduced by Alain-Sol Sznitman in arXiv:1209.4531, and show that: the interlacement set is "well-connected", i.e., any two "sausages" in $d$-dimensional Brownian interlacements, $d\geq 3$, can be connected via no more than $\lceil (d-4)/2 \rceil$ intermediate sausages almost surely; while the vacant set undergoes a non-trivial percolation phase transition when the level parameter varies.

math.PR↗

arXiv2019

Risk Management via Anomaly Circumvent: Mnemonic Deep Learning for Midterm Stock Prediction

Midterm stock price prediction is crucial for value investments in the stock market. However, most deep learning models are essentially short-term and applying them to midterm predictions encounters large cumulative errors because they cannot avoid anomalies. In this paper, we propose a novel deep neural network Mid-LSTM for midterm stock prediction, which incorporates the market trend as hidden states. First, based on the autoregressive moving average model (ARMA), a midterm ARMA is formulated by taking into consideration both hidden states and the capital asset pricing model. Then, a midterm LSTM-based deep neural network is designed, which consists of three components: LSTM, hidden Markov model and linear regression networks. The proposed Mid-LSTM can avoid anomalies to reduce large prediction errors, and has good explanatory effects on the factors affecting stock prices. Extensive experiments on S&P 500 stocks show that (i) the proposed Mid-LSTM achieves 2-4% improvement in prediction accuracy, and (ii) in portfolio allocation investment, we achieve up to 120.16% annual return and 2.99 average Sharpe ratio.

q-fin.ST↗

arXiv2019

Optimistic Bull or Pessimistic Bear: Adaptive Deep Reinforcement Learning for Stock Portfolio Allocation

Portfolio allocation is crucial for investment companies. However, getting the best strategy in a complex and dynamic stock market is challenging. In this paper, we propose a novel Adaptive Deep Deterministic Reinforcement Learning scheme (Adaptive DDPG) for the portfolio allocation task, which incorporates optimistic or pessimistic deep reinforcement learning that is reflected in the influence from prediction errors. Dow Jones 30 component stocks are selected as our trading stocks and their daily prices are used as the training and testing data. We train the Adaptive DDPG agent and obtain a trading strategy. The Adaptive DDPG's performance is compared with the vanilla DDPG, Dow Jones Industrial Average index and the traditional min-variance and mean-variance portfolio allocation strategies. Adaptive DDPG outperforms the baselines in terms of the investment return and the Sharpe ratio.

q-fin.ST↗

arXiv2018

Sparse Model Identification and Learning for Ultra-high-dimensional Additive Partially Linear Models

The additive partially linear model (APLM) combines the flexibility of nonparametric regression with the parsimony of regression models, and has been widely used as a popular tool in multivariate nonparametric regression to alleviate the "curse of dimensionality". A natural question raised in practice is the choice of structure in the nonparametric part, that is, whether the continuous covariates enter into the model in linear or nonparametric form. In this paper, we present a comprehensive framework for simultaneous sparse model identification and learning for ultra-high-dimensional APLMs where both the linear and nonparametric components are possibly larger than the sample size. We propose a fast and efficient two-stage procedure. In the first stage, we decompose the nonparametric functions into a linear part and a nonlinear part. The nonlinear functions are approximated by constant spline bases, and a triple penalization procedure is proposed to select nonzero components using adaptive group LASSO. In the second stage, we refit data with selected covariates using higher order polynomial splines, and apply spline-backfitted local-linear smoothing to obtain asymptotic normality for the estimators. The procedure is shown to be consistent for model structure identification. It can identify zero, linear, and nonlinear components correctly and efficiently. Inference can be made on both linear coefficients and nonparametric functions. We conduct simulation studies to evaluate the performance of the method and apply the proposed method to a dataset on the Shoot Apical Meristem (SAM) of maize genotypes for illustration.

stat.ME↗

arXiv2018

One-point function estimates for loop-erased random walk in three dimensions

In this work, we consider loop-erased random walk (LERW) in three dimensions and give an asymptotic estimate on the one-point function for LERW and the non-intersection probability of LERW and simple random walk in three dimensions for dyadic scales. These estimates will be crucial to the characterization of the convergence of LERW to its scaling limit in natural parametrization. As a step in the proof, we also obtain a coupling of two pairs of LERW and SRW with different starting points conditioned to avoid each other.

math.PR↗

arXiv2018

Shape theorem and surface fluctuation for Poisson cylinders

In this work, we prove a shape theorem for Poisson cylinders and give a power law bound on surface fluctuations. We prove that for any $a \in (1/2, 1)$, conditioned on the origin being in the set of cylinders, every point in this set, whose Euclidean norm is less than $R$, lies at an internal distance less than $R+O(R^a)$ from the origin.

math.PR↗

arXiv2015

Making Availability as a Service in the Clouds

Cloud computing has achieved great success in modern IT industry as an excellent computing paradigm due to its flexible management and elastic resource sharing. To date, cloud computing takes an irrepalceable position in our socioeconomic system and influences almost every aspect of our daily life. However, it is still in its infancy, many problems still exist.Besides the hotly-debated security problem, availability is also an urgent issue.With the limited power of availability mechanisms provided in present cloud platform, we can hardly get detailed availability information of current applications such as the root causes of availability problem,mean time to failure, etc. Thus a new mechanism based on deep avaliability analysis is neccessary and benificial.Following the prevalent terminology 'XaaS',this paper proposes a new win-win concept for cloud users and providers in term of 'Availability as a Service' (abbreviated as 'AaaS').The aim of 'AaaS' is to provide comprehensive and aimspecific runtime avaliabilty analysis services for cloud users by integrating plent of data-driven and modeldriven approaches. To illustrate this concept, we realize a prototype named 'EagleEye' with all features of 'AaaS'. By subscribing corresponding services in 'EagleEye', cloud users could get specific availability information of their applications deployed in cloud platform. We envision this new kind of service will be merged into the cloud management mechanism in the near future.

cs.DC↗

arXiv2014

A lower bound for disconnection by simple random walk

We consider simple random walk on Z^d, d bigger or equal to 3. Motivated by the work of A.-S. Sznitman and the author in arXiv:1304.7477 and arXiv:1310.2177, we investigate the asymptotic behaviour of the probability that a large body gets disconnected from infinity by the set of points visited by a simple random walk. We derive asymptotic lower bounds that bring into play random interlacements. Although open at the moment, some of the lower bounds that we obtain possibly match the asymptotic upper bounds obtained in a recent article of A.-S. Sznitman. This potentially yields special significance to the tilted walks that we use in this work, and to the strategy that we employ to implement disconnection.

math.PR↗

arXiv2014

Large deviations for occupation time profiles of random interlacements

We derive a large deviation principle for the density profile of occupation times of random interlacements at a fixed level in a large box of Z^d, with d bigger or equal to 3. As an application, we analyze the asymptotic behavior of the probability that atypically high values of the density profile insulate a macroscopic body in a large box. As a step in this program, we obtain a similar large deviation principle for the occupation-time measure of Brownian interlacements at a fixed level in a large box of R^d, and we derive a new identity for the Laplace transform of the occupation-time measure, which is based on the analysis of certain Schrödinger semi-groups.

math.PR↗

arXiv2014

A lower bound for disconnection by random interlacements

We consider the vacant set of random interlacements on Z^d, with d bigger or equal to 3, in the percolative regime. Motivated by the large deviation principles obtained in our recent work arXiv:1304.7477, we investigate the asymptotic behavior of the probability that a large body gets disconnected from infinity by the random interlacements. We derive an asymptotic lower bound, which brings into play tilted interlacements, and relates the problem to some of the large deviations of the occupation-time profile considered in arXiv:1304.7477.

math.PR↗