Searcharxiv⌕ Search

arXiv subjects

Jianwei Shi

Publications and source records attributed to Jianwei Shi.

8 recordsLinked to original sources
arXiv2026

Decentralized Sparse Quantile Regression

Distributed statistical learning has recently attracted significant attention owing to its computational efficiency and scalability in large-scale systems. However, the non-smooth quantile loss poses substantial challenges to the development of efficient decentralized algorithms for quantile regression. Existing methods may either suffer from slow convergence or rely on smoothing-based approximations that require additional stringent assumptions, particularly in high-dimensional settings. To address these issues, we propose a decentralized framework that integrates gradient tracking with iterative hard thresholding for sparse quantile estimation. The proposed method avoids smoothing approximations and relaxes the initialization requirement. Theoretically, we show that the proposed algorithm achieves linear convergence under stated regularity conditions and that the resulting estimator attains the same order of statistical accuracy as its centralized counterpart. We further develop a decentralized information criterion for selecting the working sparsity level and establish support screening guarantees. Numerical experiments and a real-data study illustrate the finite-sample performance of the proposed method.

stat.ME↗
arXiv2026

K-energy for the coupled constant scalar curvature Kähler equation, I: Slope formula and semistability

In this paper we study coupled constant scalar curvature Kähler metrics defined by Datar-Pingali extending coupled Kähler-Einstein metrics defined by Hultgren-Witt Nyström. We consider two K-energy functionals of which one (denoted $\mathcal{M}_{\operatorname{ccscK}}$) integrates the moment map considered by Datar-Pingali and the other (denoted $\mathcal{M}'$) is designed so that its slope at infinity for subgeodesic rays for ample test configurations with reduced central fiber coincides with the Donaldson-Futaki invariant considered by Hultgren-Witt Nyström and Datar-Pingali. We also extend $\mathcal{M}_{\operatorname{ccscK}}$ to $\mathcal{H}^{1,\bar{1}}$ and the finite energy class $\mathcal{E}^1$, and prove its convexity along tuples of weak geodesics and finite energy geodesics, respectively. As a corollary, we obtain a semistability condition necessary for the existence of ccscK metrics.

math.DG↗
arXiv2025

Scalable Asynchronous Federated Modeling for Spatial Data

Spatial data are central to applications such as environmental monitoring and urban planning, but are often distributed across devices where privacy and communication constraints limit direct sharing. Federated modeling offers a practical solution that preserves data privacy while enabling global modeling across distributed data sources. For instance, environmental sensor networks are privacy- and bandwidth-constrained, motivating federated spatial modeling that shares only privacy-preserving summaries to produce timely, high-resolution pollution maps without centralizing raw data. However, existing federated modeling approaches either ignore spatial dependence or rely on synchronous updates that suffer from stragglers in heterogeneous environments. This work proposes an asynchronous federated modeling framework for spatial data based on low-rank Gaussian process approximations. The method employs block-wise optimization and introduces strategies for gradient correction, adaptive aggregation, and stabilized updates. We establish linear convergence with explicit dependence on staleness, a result of standalone theoretical significance. Moreover, numerical experiments demonstrate that the asynchronous algorithm achieves synchronous performance under balanced resource allocation and significantly outperforms it in heterogeneous settings, showcasing superior robustness and scalability.

stat.ME↗
arXiv2025

Decentralized Inference for Spatial Data Using Low-Rank Models

Advancements in information technology have enabled the creation of massive spatial datasets, driving the need for scalable and efficient computational methodologies. While offering viable solutions, centralized frameworks are limited by vulnerabilities such as single-point failures and communication bottlenecks. This paper presents a decentralized framework tailored for parameter inference in spatial low-rank models to address these challenges. A key obstacle arises from the spatial dependence among observations, which prevents the log-likelihood from being expressed as a summation-a critical requirement for decentralized optimization approaches. To overcome this challenge, we propose a novel objective function leveraging the evidence lower bound, which facilitates the use of decentralized optimization techniques. Our approach employs a block descent method integrated with multi-consensus and dynamic consensus averaging for effective parameter optimization. We prove the convexity of the new objective function in the vicinity of the true parameters, ensuring the convergence of the proposed method. Additionally, we present the first theoretical results establishing the consistency and asymptotic normality of the estimator within the context of spatial low-rank models. Extensive simulations and real-world data experiments corroborate these theoretical findings, showcasing the robustness and scalability of the framework.

stat.ML↗
arXiv2022

Reinforcement Learning based Voice Interaction to Clear Path for Robots in Elevator Environment

Efficient use of the space in an elevator is very necessary for a service robot, due to the need for reducing the amount of time caused by waiting for the next elevator. To provide a solution for this, we propose a hybrid approach that combines reinforcement learning (RL) with voice interaction for robot navigation in the scene of entering the elevator. RL provides robots with a high exploration ability to find a new clear path to enter the elevator compared to traditional navigation methods such as Optimal Reciprocal Collision Avoidance (ORCA). The proposed method allows the robot to take an active clear path action towards the elevator whilst a crowd of people stands at the entrance of the elevator wherein there are still lots of space. This is done by embedding a clear path action (voice prompt) into the RL framework, and the proposed navigation policy helps the robot to finish tasks efficiently and safely. Our model approach provides a great improvement in the success rate and reward of entering the elevator compared to state-of-the-art navigation policies without active clear path operation.

cs.RO↗
arXiv2021

Viewing Vision Videos Online: Opportunities for Distributed Stakeholders

Creating shared understanding between stakeholders is essential for the success of software projects. Conflicting requirements originating from misaligned mental models can hinder the development process. The use of videos to present abstract system visions is one approach to counteract this problem. These videos are usually shown in in-person meetings. However, face-to-face meetings are not suited to every situation and every stakeholder, for example due to scheduling constraints. Methods for the use of vision videos in online settings are necessary. Furthermore, methods enabling an asynchronous use of vision videos are needed for cases when conjoined meetings are impossible even in an online setting. In this paper, we compare synchronous and asynchronous viewings of vision videos in online settings. The two methods are piloted in a preliminary experiment. The results show a difference in the amount of arguments regarding the presented visions. On average, participants who took part in asynchronous meetings stated more arguments. Our results point to multiple advantages and disadvantages as well as use cases for each type. For example, a synchronous meeting could be chosen when all involved stakeholders can attend the appointment to discuss the vision and to quickly resolve ambiguities. An asynchronous meeting could be held if a joint meeting is not feasible due to time constraints. We also discuss how our findings can be applied to the elicitation of requirements from a crowd of stakeholders.

cs.SE↗
arXiv2020

Investigating Correlations of Automatically Extracted Multimodal Features and Lecture Video Quality

Ranking and recommendation of multimedia content such as videos is usually realized with respect to the relevance to a user query. However, for lecture videos and MOOCs (Massive Open Online Courses) it is not only required to retrieve relevant videos, but particularly to find lecture videos of high quality that facilitate learning, for instance, independent of the video's or speaker's popularity. Thus, metadata about a lecture video's quality are crucial features for learning contexts, e.g., lecture video recommendation in search as learning scenarios. In this paper, we investigate whether automatically extracted features are correlated to quality aspects of a video. A set of scholarly videos from a Mass Open Online Course (MOOC) is analyzed regarding audio, linguistic, and visual features. Furthermore, a set of cross-modal features is proposed which are derived by combining transcripts, audio, video, and slide content. A user study is conducted to investigate the correlations between the automatically collected features and human ratings of quality aspects of a lecture video. Finally, the impact of our features on the knowledge gain of the participants is discussed.

cs.MM↗