Data Science, Where Statistics Meets Optimization

J. Lederer

{}^{1}

${}^{1}$

Departament of Mathematics, University of Hamburg [johannes.lederer@uni-hamburg.de]

Keywords: Data science – Deep learning – Extreme-value theory – Optimization

Abstract

Modern data science spans computer science, mathematics, and applications. Hence, these different fields need to support and nourish each other in order to reach the full potential of data science. This talk will bring a sharp focus on the roles of statistics and optimization. We will discuss two examples: We start with deep learning, where mathematical statistics can lead to a more profound understanding of computer-science pipelines. We then turn to extremes, where efficient computing algorithms can lead to mathematical models for contemporary data. You will walk away from this talk with a clear understanding of how statistics and optimization can work together to improve data science.

References

Lederer [2022] Johannes Lederer. Fundamentals of high-dimensional statistics. Springer Texts in Statistics, 2022.
Lederer and Oesting [2023] Johannes Lederer and Marco Oesting. Extremes in high dimensions: Methods and scalable algorithms, 2023.
Taheri et al. [2022a] Mahsa Taheri, Néhémy Lim, and Johannes Lederer. Balancing statistical and computational precision: A general theory and applications to sparse regression. IEEE Transactions on Information Theory, 69(1):316–333, 2022a.
Taheri et al. [2022b] Mahsa Taheri, Fang Xie, and Johannes Lederer. Statistical guarantees for approximate stationary points of simple neural networks, 2022b.