Estimating Cosmological Parameters from the Dark Matter Distribution

A grand challenge of the 21st century cosmology is to accurately estimate the cosmological parameters of our Universe. A major approach in estimating the cosmological parameters is to use the large scale matter distribution of the Universe. Galaxy surveys provide the means to map out cosmic large-scale structure in three dimensions. Information about galaxy locations is typically summarized in a "single" function of scale, such as the galaxy correlation function or power-spectrum. We show that it is possible to estimate these cosmological parameters directly from the distribution of matter. This paper presents the application of deep 3D convolutional networks to volumetric representation of dark-matter simulations as well as the results obtained using a recently proposed distribution regression framework, showing that machine learning techniques are comparable to, and can sometimes outperform, maximum-likelihood point estimates using "cosmological models". This opens the way to estimating the parameters of our Universe with higher accuracy.

[1]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[2]  A. Lewis,et al.  Cosmological parameters from CMB and other data: A Monte Carlo approach , 2002, astro-ph/0205436.

[3]  Scott Croom,et al.  The WiggleZ Dark Energy Survey: Final data release and cosmological results , 2012, 1210.2130.

[4]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  G. Lazarides.  Introduction to Cosmology , 1999 .

[7]  Konstantinos Kamnitsas,et al.  Multi-scale 3D convolutional neural networks for lesion segmentation in brain MRI , 2015 .

[8]  M. Phillips,et al.  Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant , 1998, astro-ph/9805201.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Edward J. Wollack,et al.  NINE-YEAR WILKINSON MICROWAVE ANISOTROPY PROBE (WMAP) OBSERVATIONS: COSMOLOGICAL PARAMETER RESULTS , 2012, 1212.5226.

[11]  J. Peacock,et al.  Stable clustering, the halo model and non-linear cosmological power spectra , 2002, astro-ph/0207664.

[12]  Max Welling,et al.  Learning the Irreducible Representations of Commutative Lie Groups , 2014, ICML.

[13]  Pedro M. Domingos,et al.  Deep Symmetry Networks , 2014, NIPS.

[14]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[15]  R. Wilson.  Modern Cosmology , 2004 .

[16]  Pablo Fosalba,et al.  ICE-COLA: towards fast and accurate synthetic galaxy catalogues optimizing a quasi-N-body method , 2015, 1509.04685.

[17]  Sander Dieleman,et al.  Rotation-invariant convolutional neural networks for galaxy morphology prediction , 2015, ArXiv.

[18]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[19]  Daniel Thomas,et al.  The clustering of galaxies in the sdss-iii baryon oscillation spectroscopic survey: Baryon acoustic oscillations in the data release 9 spectroscopic galaxy sample , 2012, 1312.4877.

[20]  B. Laurent.  Efficient estimation of integral functionals of a density , 1996 .

[21]  A. Lewis,et al.  Efficient computation of CMB anisotropies in closed FRW models , 1999, astro-ph/9911177.

[22]  Hilo,et al.  THE ELEVENTH AND TWELFTH DATA RELEASES OF THE SLOAN DIGITAL SKY SURVEY: FINAL DATA FROM SDSS-III , 2015, 1501.00963.

[23]  V. Springel.  The Cosmological simulation code GADGET-2 , 2005, astro-ph/0505010.

[24]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[25]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[26]  H. Trac,et al.  SCORCH. I. THE GALAXY–HALO CONNECTION IN THE FIRST BILLION YEARS , 2015, 1507.02685.

[27]  Barnabás Póczos,et al.  Distribution-Free Distribution Regression , 2013, AISTATS.

[28]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[29]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[30]  Barnabás Póczos,et al.  Fast Distribution To Real Regression , 2013, AISTATS.

[31]  A. G. Alexei,et al.  OBSERVATIONAL EVIDENCE FROM SUPERNOVAE FOR AN ACCELERATING UNIVERSE AND A COSMOLOGICAL CONSTANT , 1998 .

[32]  Ronald M. Summers,et al.  Deep convolutional networks for pancreas segmentation in CT imaging , 2015, Medical Imaging.

[33]  R. Ellis,et al.  The 2dF Galaxy Redshift Survey: power-spectrum analysis of the final data set and cosmological implications , 2005, astro-ph/0501174.

[34]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[35]  Felipe Marin,et al.  Fast and accurate mock catalogue generation for low-mass galaxies , 2015, 1507.05329.

[36]  R. Ellis,et al.  Measurements of $\Omega$ and $\Lambda$ from 42 high redshift supernovae , 1998, astro-ph/9812133.

[37]  Jean-Michel Marin,et al.  Approximate Bayesian computational methods , 2011, Statistics and Computing.

[38]  Yu. I. Ingster,et al.  Estimation and detection of functions from anisotropic Sobolev classes , 2011 .

[39]  C. A. Oxborrow,et al.  Planck2015 results , 2015, Astronomy & Astrophysics.

[40]  Matias Zaldarriaga,et al.  Solving large scale structure in ten easy steps with COLA , 2013, 1301.0322.

[41]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[42]  Alexandre B. Tsybakov,et al.  Introduction to Nonparametric Estimation , 2008, Springer series in statistics.