Speaker
Description
Machine learning is increasingly shaping cosmological analyses, though its impact depends critically on careful validation and physically interpretable use. In this talk, I will outline several AI/ML approaches for model-independent cosmological inference, with an emphasis on how data-driven methods can complement more traditional statistical techniques. I will discuss LADDER [1], a deep-learning framework for reconstructing the cosmic distance ladder directly from Type Ia supernovae (SNIa) data while incorporating the full covariance structure of the observations. Following extensive robustness tests, LADDER provides reliable predictions that enable model-independent applications such as consistency checks of baryon acoustic oscillation measurements [2], calibration of high-redshift datasets (e.g., gamma-ray bursts), and the construction of mock catalogues for future SNIa and gravitational-wave (GW) missions. These examples illustrate how carefully validated deep-learning tools can assist cosmological analyses without assuming specific parametric forms. I will also briefly discuss Gaussian-process-based reconstruction of the Hubble parameter and its use in examining the potential cosmological implications of future GW observations [3,4]. Taken together, these methods aim to demonstrate both the potential and the necessary caution, in applying AI/ML techniques to cosmology, and show how responsible non-parametric approaches may offer fresh perspectives on several ongoing challenges in precision cosmology. [1] R. Shah, S. Saha, P. Mukherjee, U. Garain and S. Pal, ApJS 273, 27 (2024) doi:10.3847/15384365/ad5558 [arXiv:2401.17029 [astro-ph.CO]]. [2] R. Shah, P. Mukherjee, S. Saha, U. Garain and S. Pal, [arXiv:2412.14750 [astro-ph.CO]]. [3] R. Shah, A. Bhaumik, P. Mukherjee and S. Pal, JCAP 06, 038 (2023) doi:10.1088/14757516/2023/06/038 [arXiv:2301.12708 [astro-ph.CO]]. [4] P. Mukherjee, R. Shah, A. Bhaumik and S. Pal, Astrophys. J. 960, no.1, 61 (2024) doi:10.3847/15384357/ad055f [arXiv:2303.05169 [astro-ph.CO]].