The upcoming era of cosmological surveys promises an unprecedented wealth of observational data that will transform our understanding of the universe. Surveys such as DESI, Euclid, and the Vera C. Rubin Observatory will provide extremely detailed maps of billions of galaxies out to high redshifts. Analyzing these massive datasets poses exciting challenges that machine learning is uniquely poised to help overcome. In this talk, I will highlight recent examples from my work on probabilistic machine learning for cosmology. First, I will explain how a point cloud diffusion model can be used both as a generative model for 3D maps of galaxy clustering and as a likelihood model for such datasets. Moreover, I will present a generative model developed to reconstruct the initial conditions of the Universe from spectroscopic survey observations. When combined with the wealth of data from upcoming surveys, these machine learning techniques have the potential to provide new insights into fundamental questions about the nature of the universe.

The astronomy community is facing an unprecedented data influx from next-generation observatories, challenging traditional analytical methods. Artificial Intelligence (AI) is emerging as a key tool to handle these vast, complex datasets, uncovering hidden patterns and accelerating discoveries. This talk will explore how AI is transforming the field, addressing the unique challenges of astronomical data, and highlighting opportunities for new breakthroughs. As we embrace this AI-driven era, the collaboration between AI and astronomy will be crucial for shaping the future of astronomical research.

Artificial intelligence (AI) is a potentially disruptive tool for physics and science in general. One crucial question is how this technology can contribute at a conceptual level to help acquire new scientific understanding or inspire new surprising ideas. I will talk about how AI can be used as an artificial muse in physics, which suggests surprising and unconventional ideas and techniques that the human scientist can interpret, understand and generalize to its fullest potential.

[1] Krenn, Kottmann, Tischler, Aspuru-Guzik, Conceptual understanding through efficient automated design of quantum optical experiments. Physical Review X 11(3), 031044 (2021).

[2] Krenn, Pollice, Guo, Aldeghi, Cervera-Lierta, Friederich, Gomes, Häse, Jinich, Nigam, Yao, Aspuru-Guzik, On scientific understanding with artificial intelligence. Nature Reviews Physics 4, 761–769 (2022).

[3] Krenn et al., Forecasting the future of artificial intelligence with machine learning-based link prediction in an exponentially growing knowledge network, Nature Machine Intelligence 5, 1326 (2023)

Particle physics has a rich history of using and developing AI. However, during the past decade, the relationship between AI and particle physics has substantially changed, evolving from the use of simple feed forward neural networks for event selection to the development of cutting edge foundation models and novel AI methodologies. This talk will explore the state of the art in current AI and particle physics research, including foundation and language models, simulation based inference, diffusion models, geometric deep learning, and unfolding. I will also share open challenges that still remain when using AI for particle physics and science more broadly, including uncertainty quantification, tension between simulation and nature, the role of inductive biases, and the nature of scientific knowledge itself.

Goodness of fit is the statistical problem of assessing the compatibility of data with their hypothesised distribution. It can be turned into a 2-sample test, if the distribution is samplable. I will discuss how the problem can be tackled as a two-hypotheses Neyman-Pearson test, and how this approach straightforwardly leads to the NPLM (New Physics Learning Machine) method. A comparative performance study with classical and Machine-Learning-based approaches to Goodness of Fit is presented. Possible applications are model-agnostic searches for new physics at the LHC, the monitoring of complex apparatuses and the validation of Generative Models.