A Brief History of Inference in Astronomy

TL;DR

This paper reviews the evolution of inference methods in astronomy, emphasizing the transition from classical optimization to Bayesian and deep learning techniques, and discusses how adaptive models influence scientific data analysis.

Contribution

It provides a concise overview of key historical shifts in inference methods in astronomy, highlighting recent advances and their impact on research practices.

Findings

Shift from classical optimization to Bayesian inference

Rise of gradient-based methods driven by deep learning

Development of adaptive models shaping data collection

Abstract

In this short review, we trace the evolution of inference in astronomy, highlighting key milestones rather than providing an exhaustive survey. We focus on the shift from classical optimization to Bayesian inference, the rise of gradient-based methods fueled by advances in deep learning, and the emergence of adaptive models that shape the very design of scientific datasets. Understanding this shift is essential for appreciating the current landscape of astronomical research and the future it is helping to build.