Special Issue on Mathematical Statistics of Machine Learning

Aims and Scope

Statistical Learning and Data Science (SLADS) is a newly launched journal sponsored by the Chinese Academy of Sciences, dedicated to publishing high-quality research across statistics, machine learning, artificial intelligence, and data science. SLADS emphasizes both rapid publication and rigorous peer review, using the OpenReview system to ensure transparency and quality. The editorial goal is to reach an Accept/Reject decision within 3.5 months of submission while maintaining high scholarly standards.This special issue focuses on the mathematical and statistical foundations of machine learning, highlighting rigorous theory, principled methodology, and statistical understanding of modern learning algorithms.

Submission Deadline: June 30, 2026

• Early submissions will be reviewed and published online ahead of the final issue.

Topics of Interest

We welcome original research contributions including, but not limited to:

Learning Theory

• Generalization and excess risk bounds
• Minimax theory and optimal rates
• Statistical–computational inference and estimation
• Sparsity, low-rank, and structured models

Optimization and Algorithms

• Convergence theory for stochastic and nonconvex methods
• Algorithmic stability and statistical guarantees
• Online and adaptive learning

Probabilistic Foundations

• Random matrix theory and concentration inequalities
• Empirical process theory and high-dimensional probability

Modern Learning Models

• Statistical theory of deep learning and neural networks
• Kernel methods and infinite-width limits
• Representation learning
• Generative models (including diffusion models, flow matching, and others)
• Empirical processes theory and high-dimensional probability

Guest Editors

• Cristina Butucea (CREST, ENSAE, IP PARIS)
• Anru Zhang (Duke University)
• Edgar Dobriban (University of Pennsylvania)

Submission Information

Manuscripts should be submitted through the SLADS website at http://slads.scichina.com.

Contact: Ruiyan Zhang, zhangry@scichina.com