Estimating Cosmological Parameters from the Dark Matter Distribution

Siamak Ravanbakhsh, Junier Oliva, Sebastian Fromenteau, Layne Price, Shirley Ho, Jeff Schneider, Barnabas Poczos
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2407-2416, 2016.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v48-ravanbakhshb16, title = {Estimating Cosmological Parameters from the Dark Matter Distribution}, author = {Ravanbakhsh, Siamak and Oliva, Junier and Fromenteau, Sebastian and Price, Layne and Ho, Shirley and Schneider, Jeff and Poczos, Barnabas}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {2407--2416}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/ravanbakhshb16.pdf}, url = {https://proceedings.mlr.press/v48/ravanbakhshb16.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Estimating Cosmological Parameters from the Dark Matter Distribution %A Siamak Ravanbakhsh %A Junier Oliva %A Sebastian Fromenteau %A Layne Price %A Shirley Ho %A Jeff Schneider %A Barnabas Poczos %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-ravanbakhshb16 %I PMLR %P 2407--2416 %U https://proceedings.mlr.press/v48/ravanbakhshb16.html %V 48 %X 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.
RIS
TY - CPAPER TI - Estimating Cosmological Parameters from the Dark Matter Distribution AU - Siamak Ravanbakhsh AU - Junier Oliva AU - Sebastian Fromenteau AU - Layne Price AU - Shirley Ho AU - Jeff Schneider AU - Barnabas Poczos BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-ravanbakhshb16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 2407 EP - 2416 L1 - http://proceedings.mlr.press/v48/ravanbakhshb16.pdf UR - https://proceedings.mlr.press/v48/ravanbakhshb16.html AB - 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. ER -
APA
Ravanbakhsh, S., Oliva, J., Fromenteau, S., Price, L., Ho, S., Schneider, J. & Poczos, B.. (2016). Estimating Cosmological Parameters from the Dark Matter Distribution. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:2407-2416 Available from https://proceedings.mlr.press/v48/ravanbakhshb16.html.

Related Material