AStA Advances in Statistical Analysis - Call for Papers: Bridging the gap between AI and Statistics

Bridging the gap between AI and Statistics

Guest Editors: David Rügamer (RWTH Aachen, LMU Munich) and Benjamin Säfken (Clausthal University of Technology)

The ever growing availability of complex heterogeneous data requires models that can work at large scale, in high-dimensional settings and have great flexibility. Methods in statistics, machine learning and at their intersection try to tackle these challenges and allow for modeling of complex data generating processes. Some applications require high predictive performance, for others interpretability and uncertainty quantification are desirable. In this special issue on Artificial Intelligence (AI) and Statistics we aim to showcase research from statistics and machine learning to demonstrate the role of these fields in AI.

We invite submissions presenting new and original research on topics including but not limited to the following:

●    Integrating structural assumptions from statistics in machine or deep learning
●    Statistical uncertainty quantification for machine learning or deep learning
●    Relationship between statistical methods and machine learning concepts 
●    Statistical analysis or adaptation of statistical methods for non-tabular data
●    Computer vision or natural language processing from a statistical point of view
●    Optimization routines relevant for both machine learning and statistics
●    The role of kernel methods in statistics and machine learning
●    The connection of boosting and statistics
●    Interpretable machine or deep learning
●    Statistics and AutoML

In line with the aims and scope of AStA - Advances in Statistical Analysis, submissions are welcome in the following two sections:

●    Applications: The application section provides a forum for innovative use of statistically inspired machine learning methods applied to relevant data problems.
●    Methodology: The methodology section publishes original articles on statistical theory and methodological developments. The contributions in this section should be motivated by problems involving both statistics and machine or deep learning.

Reproducibility. Readers should be able to reproduce the results presented in the articles. Authors are strongly encouraged to make data (or at least their simulated counterparts) and software available as electronic supplements. Code should not primarily be included in the article itself although including code snippets is fine if it supports the general aim of the article.

Deadline for submission: 30 November 2022

Submissions follow the editorial standard of AStA - Advances in Statistical Analysis.