paper-with-me

Papers

CosmoFlow: Scale-Aware Representation Learning for Cosmology with Flow Matching

2025-07-16 · Sidharth Kannan, Tian Qiu, Carolina Cuesta-Lazaro, Haewon Jeong arxiv

Generative machine learning models have been demonstrated to be able to learn low dimensional representations of data that preserve information required for downstream tasks. In this work, we demonstrate that flow matching based generative models can learn compact, semantically rich latent representations of field level cold dark matter (CDM) simulation data without supervision. Our model, CosmoFlow, learns representations 32x smaller than the raw field data, usable for field level reconstruction, synthetic data generation, and parameter inference. Our model also learns interpretable representations, in which different latent channels correspond to features at different cosmological scales.

📄 PDF Abstract BibTeX arXiv:2507.11842

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data GenerationRepresentation Learning

Similar Papers 제목 키워드 기반

CosmoFlow: Using Deep Learning to Learn the Universe at Scale

2018-08-14 · Amrita Mathuriya, Deborah Bard, Peter Mendygral, Lawrence Meadows 외

Deep learning is a promising tool to determine the physical model that describes our universe. To handle the considerable computational cost of this problem, we present CosmoFlow: a highly scalable deep learning applicat…

Deep Learning

The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism

2020-07-25 · Yosuke Oyama, Naoya Maruyama, Nikoli Dryden, Erin McCarthy 외

We present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional sample…

2k

Consistently Large Cosmic Flows on Scales of 100 Mpc/h: a Challenge for the Standard LCDM Cosmology

2008-09-23

Peculiar velocity surveys have non-uniform spatial distributions of tracers, so that the bulk flow estimated from them does not correspond to that of a simple volume such as a sphere. Thus bulk flow estimates are general…

Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology

2026-05-14 · Licong Xu, Thomas Borrett arxiv

Recent advances in artificial intelligence (AI) agents are pushing AI beyond tools toward autonomous scientific discovery. We discuss two complementary agentic systems for cosmology: \texttt{CMBEvolve}, which targets tas…

Out-of-Distribution Detection

Clairvoyant Prefetching for Distributed Machine Learning I/O

2021-01-21 · Nikoli Dryden, Roman Böhringer, Tal Ben-Nun, Torsten Hoefler

I/O is emerging as a major bottleneck for machine learning training, especially in distributed environments. Indeed, at large scale, I/O takes as much as 85% of training time. Addressing this I/O bottleneck necessitates …

BIG-bench Machine Learning