{"ID":2851447,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.19168","arxiv_id":"2510.19168","title":"Transfer Learning Beyond the Standard Model","abstract":"Machine learning enables powerful cosmological inference but typically requires many high-fidelity simulations covering many cosmological models. Transfer learning offers a way to reduce the simulation cost by reusing knowledge across models. We show that pre-training on the standard model of cosmology, $Λ$CDM, and fine-tuning on various beyond-$Λ$CDM scenarios -- including massive neutrinos, modified gravity, and primordial non-Gaussianities -- can enable inference with significantly fewer beyond-$Λ$CDM simulations. However, we also show that negative transfer can occur when strong physical degeneracies exist between $Λ$CDM and beyond-$Λ$CDM parameters. We consider various transfer architectures, finding that including bottleneck structures provides the best performance. Our findings illustrate the opportunities and pitfalls of foundation-model approaches in physics: pre-training can accelerate inference, but may also hinder learning new physics.","short_abstract":"Machine learning enables powerful cosmological inference but typically requires many high-fidelity simulations covering many cosmological models. Transfer learning offers a way to reduce the simulation cost by reusing knowledge across models. We show that pre-training on the standard model of cosmology, $Λ$CDM, and fin...","url_abs":"https://arxiv.org/abs/2510.19168","url_pdf":"https://arxiv.org/pdf/2510.19168v1","authors":"[\"Veena Krishnaraj\",\"Adrian E. Bayer\",\"Christian Kragh Jespersen\",\"Peter Melchior\"]","published":"2025-10-22T01:59:38Z","proceeding":"astro-ph.CO","tasks":"[\"astro-ph.CO\",\"astro-ph.IM\",\"cs.LG\",\"physics.data-an\"]","methods":"[]","has_code":false}