Conditional density estimation tools in python and R with applications to photometric redshifts and likelihood-free cosmological inference (2019-08-30T00:00:00.000000Z)

TL;DR

The goal of this work is to provide a comprehensive range of statistical tools and open-source software for nonparametric CDE and method assessment which can accommodate different types of settings and be easily fit to the problem at hand.

Authors

A. Malz

2 papers

Niccolò Dalmasso

1 papers

T. Pospisil

1 papers

Ann B. Lee

2 papers

Rafael Izbicki

2 papers

P. Freeman

1 papers

TL;DR

Authors

References84 items

Predicción y selección de variables con bosques aleatorios en presencia de variables correlacionadas

Evaluation of probabilistic photometric redshift estimation approaches for LSST

PyTorch: An Imperative Style, High-Performance Deep Learning Library

(f)RFCDE: Random Forests for Conditional Density Estimation and Functional Data

Automatic Posterior Transformation for Likelihood-Free Inference

Fast likelihood-free cosmology with neural density estimators and active learning

Adaptive Gaussian Copula ABC

The Role of Machine Learning in the Next Decade of Cosmology

Cosmological Constraints from Multiple Probes in the Dark Energy Survey.

Handbook of Approximate Bayesian Computation

Planck2018 results

Photometric redshifts from SDSS images using a convolutional neural network

Approximating Photo-z PDFs for Large Surveys

ABC–CDE: Toward Approximate Bayesian Computation With Complex High-Dimensional Data and Limited Simulations

RFCDE: Random Forests for Conditional Density Estimation

Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology

High redshift galaxies in the ALHAMBRA survey

Flexible statistical inference for mechanistic models of neural dynamics

Weak Lensing for Precision Cosmology

KiDS-450 + 2dFLenS: Cosmological parameter constraints from weak gravitational lensing tomography and overlapping redshift-space galaxy clustering

Dark Energy Survey Year 1 Results: Multi-Probe Methodology and Simulated Likelihood Analyses

KiDS+GAMA : cosmology constraints from a joint analysis of cosmic shear, galaxy-galaxy lensing, and angular clustering

Photometric redshift estimation via deep learning

Converting High-Dimensional Regression to High-Dimensional Conditional Density Estimation

A unified framework for constructing, tuning and assessing photometric redshift density estimates in a selection bias setting

On the realistic validation of photometric redshifts

Data-driven, Interpretable Photometric Redshifts Trained on Heterogeneous and Unrepresentative Data

Uncertain Photometric Redshifts

Fast $\epsilon$-free Inference of Simulation Models with Bayesian Conditional Density Estimation

ABC random forests for Bayesian parameter inference

Photo-z Estimation: An Example of Nonparametric Conditional Density Estimation under Selection Bias

Nonparametric Conditional Density Estimation in a High-Dimensional Regression Setting

XGBoost: A Scalable Tree Boosting System

A Spectral Series Approach to High-Dimensional Nonparametric Regression

Learning Structured Output Representation using Deep Conditional Generative Models

Image Orientation Estimation with Convolutional Networks

Measuring photometric redshifts using galaxy images and Deep Neural Networks

Extending approximate Bayesian computation methods to high dimensions via a Gaussian copula model

THE ELEVENTH AND TWELFTH DATA RELEASES OF THE SLOAN DIGITAL SKY SURVEY: FINAL DATA FROM SDSS-III

Adam: A Method for Stochastic Optimization

GalSim: The modular galaxy image simulation toolkit

Validation of Bayesian posterior distributions using a multidimensional Kolmogorov-Smirnov test

Sparse representation of photometric redshift probability density functions: preparing for petascale astronomy

High-Dimensional Density Ratio Estimation with Extensions to Approximate Likelihood Computation

Statistics, Data Mining, and Machine Learning in Astronomy: A Practical Python Guide for the Analysis of Survey Data

Learning Stochastic Feedforward Neural Networks

SKYNET: an efficient and robust neural network training tool for machine learning in astronomy

TPZ: photometric redshift PDFs and ancillary information by using prediction trees and random forests

Introduction to astroML: Machine learning for astrophysics

ImageNet classification with deep convolutional neural networks

Advances in Machine Learning and Data Mining for Astronomy

Advances in Machine Learning and Data Mining for Astronomy

PHOTOMETRIC REDSHIFT PROBABILITY DISTRIBUTIONS FOR GALAXIES IN THE SDSS DR8

Scikit-learn: Machine Learning in Python

Data Mining and Machine Learning in Astronomy

Photometric Redshift Estimation Using Spectral Connectivity Analysis

WHAT LIES BENEATH: USING p(z) TO REDUCE SYSTEMATIC PHOTOMETRIC REDSHIFT ERRORS

EXPLOITING LOW-DIMENSIONAL STRUCTURE IN ASTRONOMICAL SPECTRA

LSST: From Science Drivers to Reference Design and Anticipated Data Products

Estimating the redshift distribution of photometric galaxy samples – II. Applications and tests of a new method

Weak Gravitational Lensing and Its Cosmological Applications

Sparse additive models

Precision photometric redshift calibration for galaxy–galaxy weak lensing

Quantile Regression Forests

Cosmology with weak lensing surveys

Approximate Bayesian computation in population genetics.

A Simple Approach to Ordinal Classification

On the multivariate probability integral transformation

Evidence and Credibility: Full Bayesian Significance Test for Precise Hypotheses

2019b, tpospisi/RFCDE 0.3.2

2019, (In Preparation) Under internal review by LSST-DESC

2019a, tpospisi/NNKCDE 0.3, doi:10.5281/zenodo.3364858, https://doi.org/10.5281/zenodo.3364858

2018, hdrcde: Highest Density Regions and Conditional Density Estimation. https: //cran.r-project.org/web/packages/hdrcde/hdrcde.pdf

2017, Data Products Definition Document, https://docushare.lsstcorp.org/docushare/dsweb/Get

Deep Learning

TensorFlow: Large-Scale Machine

pphoto(x)/pspec(x). An example of how to estimate such weights can be found in Izbicki et al