Special Issue "Methods and Applications of Data Management and Analytics"

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 31 August 2023 | Viewed by 647

Special Issue Editors

School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia
Interests: spatial-temporal data management; graph data analysis; big data analytics; stream processing and uncertain data management
Special Issues, Collections and Topics in MDPI journals
School of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, Australia
Interests: graph data processing; distributed data processing; database systems

Special Issue Information

Dear Colleagues,

Data management and analysis have recently attracted widespread attention from academia and industry due to emerging technologies powered by, and contributing to, exponential data growth. The large volume, high velocity, and wide variety of data not only pose new challenges in efficiently managing and analyzing the data, but also bring opportunities to explore the potential value of data. Therefore, this Special Issue intends to present new methods and applications in the field of data management and analysis.

We invite the submission of original research contributions in areas including, but not limited to, big data processing, data mining, data engineering, data stream systems, data security and privacy, data quality management, database systems, database theory, semi-structured data management, graph data processing, spatial and temporal data processing, uncertain and probabilistic data management, AI for database systems, and novel applications in data science.

Prof. Dr. Wenjie Zhang
Dr. Zhengyi Yang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2300 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • data management and analysis
  • big data processing
  • AI for database systems
  • data mining and models
  • data stream systems
  • data security and privacy
  • graph data processing
  • spatial and temporal data processing
  • uncertain and probabilistic data management
  • data quality management

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Implicit Bias of Deep Learning in the Large Learning Rate Phase: A Data Separability Perspective
Appl. Sci. 2023, 13(6), 3961; https://doi.org/10.3390/app13063961 - 20 Mar 2023
Viewed by 328
Abstract
Previous literature on deep learning theory has focused on implicit bias with small learning rates. In this work, we explore the impact of data separability on the implicit bias of deep learning algorithms under the large learning rate. Using deep linear networks for [...] Read more.
Previous literature on deep learning theory has focused on implicit bias with small learning rates. In this work, we explore the impact of data separability on the implicit bias of deep learning algorithms under the large learning rate. Using deep linear networks for binary classification with the logistic loss under the large learning rate regime, we characterize the implicit bias effect with data separability on training dynamics. From a data analytics perspective, we claim that depending on the separation conditions of data, the gradient descent iterates will converge to a flatter minimum in the large learning rate phase, which results in improved generalization. Our theory is rigorously proven under the assumption of degenerate data by overcoming the difficulty of the non-constant Hessian of logistic loss and confirmed by experiments on both experimental and non-degenerated datasets. Our results highlight the importance of data separability in training dynamics and the benefits of learning rate annealing schemes using an initial large learning rate. Full article
(This article belongs to the Special Issue Methods and Applications of Data Management and Analytics)
Show Figures

Figure 1

Back to TopTop