FAIR Universe: Weak Lensing ML Uncertainty Challenge Workshop

The workshop will be held on December 7, 2025 at the San Diego Convention Center in San Diego, CA, United States of America as a part of the 39th annual conference on Neural Information Processing Systems (NeurIPS).

Workshop Schedule Phase-1 Challenge Website Phase-1 Leaderboard

Workshop Schedule

Join us for the Weak Lensing ML Uncertainty Challenge Workshop at NeurIPS 2025

Date: Sunday, December 7

Time: 11:00 AM - 01:45 PM PT

Location: Exhibit Hall G,H, San Diego Convention Center

11:00 AM - 11:25 AM
Decoding the Universe with AI: A Decade of Progress and the Road Ahead François Lanusse
11:25 AM - 11:50 AM
Agents for scientific discovery Boris Bolliet
11:50 AM - 12:15 PM
FAIR Universe Weak Lensing Uncertainty Challenge Biwei Dai · Po-Wen Chang
12:15 PM - 12:20 PM
Break/Discussion
12:20 PM - 12:30 PM
Cosmological Parameter Estimation with a Denoising U-Net and Patch-Based CNNs Andry Rafaralahy
12:30 PM - 12:40 PM
Inferring Cosmological Parameters with CNN K-Fold Ensembling Andy Zhang
12:40 PM - 12:55 PM
A Domain Feature Ensemble with AdaLN Conditioned ViT for Weak Lensing Inference Haixu Wu
12:55 PM - 01:10 PM
Cosmological Parameter Estimation via Parameter-Efficient DenseNet and Tunable Loss Function Shubhojit Naskar
01:10 PM - 01:25 PM
Competing with AI Scientists: A Fully Agent-Driven Approach to Cosmological Parameter Inference Licong Xu
01:25 PM - 01:40 PM
Cosmological Parameter Estimation Under Constrained Simulation Budget with Optimal Transport-based Data Augmentation François Lanusse
01:40 PM - 01:45 PM
Phase 1 Award & Closing Remark Wahid Bhimji

For more details and uptodated schedule please check the NeurIPS Schedule.

About the Challenge

The large-scale structure of the universe—the cosmic web of galaxies, galaxy clusters, and dark matter spanning hundreds of millions of light-years—encodes essential information about the composition, evolution, and fundamental laws governing the cosmos. However, the majority of matter in the universe is dark matter, which does not interact with light and can only be observed indirectly through its gravitational effects. According to Einstein’s theory of general relativity, the gravitational field of this large-scale structure bends the path of light traveling through the universe. Weak gravitational lensing refers to the subtle, coherent distortions in the observed shapes of distant galaxies caused by the deflection of light as it traverses the inhomogeneous matter distribution of the universe. By statistically analyzing these distortions across large regions of the sky, weak lensing provides a powerful probe of the matter distribution and the underlying cosmological model that governs the expansion of the universe.

Traditional analysis based on two-point correlation functions can only capture limited amount of information from the weak lensing data (2D fields similar to images). To fully exploit the non-Gaussian features present in the cosmic web, higher-order statistics and modern machine learning (ML) methods have become increasingly important. These approaches, including deep learning and simulation-based inference, have been shown to extract significant more information in weak lensing maps than traditional techniques. However, different analyses assume different dataset setups and lead to different results, making it hard to directly compare with existing approaches. Furthermore, most (if not all) of these methods rely heavily on simulations that may not accurately represent real data due to modeling approximations and missing systematics.

This competition is motivated by the need to quantify and compare the information content that different analysis methods—ranging from classical statistics to ML-based models—can extract from weak lensing maps, while also evaluating their robustness to simulation inaccuracies and observational systematics.

The outcomes of this competition are expected to guide the development of next-generation weak lensing analysis pipelines, foster cross-disciplinary collaboration between the astrophysics and machine learning communities, and ultimately improve the reliability of cosmological inference from current and upcoming surveys such as LSST, Euclid, and the Roman Space Telescope. By explicitly addressing simulation-model mismatch and the need to quantify systematic uncertainties, this competition emphasizes scientific robustness and interpretability, aligning with the growing emphasis on trustworthy ML in scientific domains.

Organizers

We gratefully acknowledge the efforts of the FAIR Universe Team, composed of researchers dedicated to advancing high energy physics, cosmology, and machine learning for the benefit of the scientific community.

For inquiries, please contact us at: fair-universe@lbl.gov

  • Wahid Bhimji
  • Paolo Calafiura
  • Ragansu Chakkappai
  • Po-Wen Chang
  • Yuan-Tang Chou
  • Biwei Dai
  • Sascha Diefenbacher
  • Steven Farrell
  • Aishik Ghosh
  • Isabelle Guyon
  • Chris Harris
  • Shih-Chieh Hsu
  • Elham Khoda
  • Benjamin Nachman
  • Peter Nugent
  • David Rousseau
  • Uros Seljak
  • Benjamin Thorne
  • Ihsan Ullah
  • Daniel Whiteson
  • Yulei Zhang

Competition Material

Find all the competition resources below: