A Hybrid Deep Learning Approach to Cosmological Constraints from Galaxy Redshift Surveys
Michelle Ntampaka,Michelle Ntampaka,Daniel J. Eisenstein,Sihan Yuan,Lehman H. Garrison,Lehman H. Garrison +5 more
Reads0
Chats0
TLDR
A deep machine learning (ML)-based technique for accurately determining $\sigma_8$ and $\Omega_m$ from mock 3D galaxy surveys is presented and a hybrid approach that merges the two to combine physically motivated summary statistics with flexible CNNs is explored.Abstract:
We present a deep machine learning (ML)-based technique for accurately determining $\sigma_8$ and $\Omega_m$ from mock 3D galaxy surveys. The mock surveys are built from the AbacusCosmos suite of $N$-body simulations, which comprises 40 cosmological volume simulations spanning a range of cosmological models, and we account for uncertainties in galaxy formation scenarios through the use of generalized halo occupation distributions (HODs). We explore a trio of ML models: a 3D convolutional neural network (CNN), a power-spectrum-based fully connected network, and a hybrid approach that merges the two to combine physically motivated summary statistics with flexible CNNs. We describe best practices for training a deep model on a suite of matched-phase simulations and we test our model on a completely independent sample that uses previously unseen initial conditions, cosmological parameters, and HOD parameters. Despite the fact that the mock observations are quite small ($\sim0.07h^{-3}\,\mathrm{Gpc}^3$) and the training data span a large parameter space (6 cosmological and 6 HOD parameters), the CNN and hybrid CNN can constrain $\sigma_8$ and $\Omega_m$ to $\sim3\%$ and $\sim4\%$, respectively.read more
Citations
More filters
Journal ArticleDOI
The camels project: Cosmology and astrophysics with machine learning simulations
Francisco Villaescusa-Navarro,Daniel Anglés-Alcázar,Shy Genel,David N. Spergel,Rachel S. Somerville,Romeel Davé,Annalisa Pillepich,Lars Hernquist,Dylan Nelson,Paul Torrey,Desika Narayanan,Yin Li,Oliver H. E. Philcox,Valentina La Torre,Ana Maria Delgado,Shirley Ho,Shirley Ho,Sultan Hassan,Blakesley Burkhart,Digvijay Wadekar,Nicholas Battaglia,Gabriella Contardo,Greg L. Bryan +22 more
Journal ArticleDOI
The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
Francisco Villaescusa-Navarro,Daniel Anglés-Alcázar,Shy Genel,David N. Spergel,Rachel S. Somerville,Romeel Davé,Annalisa Pillepich,Lars Hernquist,Dylan Nelson,Paul Torrey,Desika Narayanan,Yin Li,Oliver H. E. Philcox,Valentina La Torre,Ana Maria Delgado,Shirley Ho,Sultan Hassan,Blakesley Burkhart,Digvijay Wadekar,Nicholas Battaglia,Gabriella Contardo +20 more
TL;DR: The Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project as mentioned in this paper provides theory predictions for different observables as a function of cosmology and astrophysics, and is the largest suite of cosmological (magneto-)hydrodynamic simulations designed to train machine learning algorithms.
Journal ArticleDOI
Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms
João Caldeira,Brian Nord +1 more
TL;DR: Three of the most common uncertainty quantification methods - Bayesian Neural Networks, Concrete Dropout, and Deep Ensembles - are compared to the standard analytic error propagation and made some recommendations for usage and interpretation of UQ methods.
Journal ArticleDOI
Large-scale dark matter simulations
Raul E. Angulo,Oliver Hahn +1 more
TL;DR: In this article , a review of collisionless numerical simulations for the large-scale structure of the universe is provided, and the main set of equations solved by these simulations and their connection with General Relativity are discussed.
Journal ArticleDOI
The Las Campanas Redshift Survey
Stephen A. Shectman,Stephen D. Landy,Augustus Oemler,Douglas L. Tucker,Huan Lin,Robert P. Kirshner,Paul L. Schechter +6 more
TL;DR: The Las Campanas Redshift Survey (LCRS) as mentioned in this paper consists of 26418 redshifts of galaxies selected from a CCD-based catalog obtained in the $R$ band.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Journal ArticleDOI
Deep learning in neural networks
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Proceedings ArticleDOI
TensorFlow: a system for large-scale machine learning
Martín Abadi,Paul Barham,Jianmin Chen,Zhifeng Chen,Andy Davis,Jeffrey Dean,Matthieu Devin,Sanjay Ghemawat,Geoffrey Irving,Michael Isard,Manjunath Kudlur,Josh Levenberg,Rajat Monga,Sherry Moore,Derek G. Murray,Benoit Steiner,Paul A. Tucker,Vijay K. Vasudevan,Pete Warden,Martin Wicke,Yuan Yu,Xiaoqiang Zheng +21 more
TL;DR: TensorFlow as mentioned in this paper is a machine learning system that operates at large scale and in heterogeneous environments, using dataflow graphs to represent computation, shared state, and the operations that mutate that state.
Related Papers (5)
Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
Daniel George,E. A. Huerta +1 more