Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Estimating Cosmological Parameters from the Dark Matter Distribution
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the conv-net instead of maximum-likelihood power-spectrum fitting | Cosmological parameter estimation from dark matter simulations · Dark matter simulations, z=0 | average relative error (Ωm): 0.072 -> 0.028 | Helped |
| Use the conv-net instead of maximum-likelihood power-spectrum fitting | Cosmological parameter estimation from dark matter simulations · Dark matter simulations, z=0 | average relative error (σ8): 0.013 -> 0.012 | No clear effect |
| Change the sub-cube size by a factor of two (ablation) | Conv-net · Dark matter simulations, z=0 | prediction accuracy | No clear effect |
| Use different spatial scales for the input cubes (ablation) | Conv-net · Dark matter simulations, z=0 | prediction accuracy | No clear effect |
| Use average pooling instead of max-pooling (ablation) | 3D conv-net · Dark matter simulations | ability to learn a meaningful model | Helped |
| Use leaky ReLU instead of non-leaky ReLU (ablation) | 3D conv-net · Dark matter simulations | learning speed | Helped |
| Add batch normalization to convolutional layers (ablation) | 3D conv-net · Dark matter simulations | training stability | Helped |
| Increase the number of conv-net layers (ablation) | 3D conv-net · Dark matter simulations | prediction performance | Helped |
| Remove two fully connected layers (ablation) | Conv-net for redshift estimation · Redshift prediction | prediction power | No clear effect |
Closest papers by meaning
- CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning (NeurIPS 2025 · similarity 0.85)
- Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields (ICLR 2025 · similarity 0.84)
- Unified Framework for Diffusion Generative Models in SO(3): Applications in Computer Vision and Astrophysics (AAAI 2024 · similarity 0.81)
- The Multimodal Universe: Enabling Large-Scale Machine Learning with 100 TB of Astronomical Scientific Data (NeurIPS 2024 · similarity 0.80)
- TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising (NeurIPS 2025 · similarity 0.80)
- A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors (NeurIPS 2025 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.