paper

paper/paper.bib

@@ -192,16 +192,14 @@ @misc{Euclid
       url={https://arxiv.org/abs/1110.3193}, 
 }
 
-@article{DESI,
-    author = "Levi, Michael E. and others",
-    collaboration = "DESI",
-    title = "{The Dark Energy Spectroscopic Instrument (DESI)}",
-    eprint = "1907.10688",
-    archivePrefix = "arXiv",
-    primaryClass = "astro-ph.IM",
-    reportNumber = "FERMILAB-PUB-19-434-AE",
-    month = "7",
-    year = "2019"
+@misc{DESI,
+      title={The Dark Energy Spectroscopic Instrument (DESI)}, 
+      author={Michael E. Levi and Lori E. Allen and Anand Raichoor and Charles Baltay and Segev BenZvi and Florian Beutler and Adam Bolton and Francisco J. Castander and Chia-Hsun Chuang and Andrew Cooper and Jean-Gabriel Cuby and Arjun Dey and Daniel Eisenstein and Xiaohui Fan and Brenna Flaugher and Carlos Frenk and Alma X. Gonzalez-Morales and Or Graur and Julien Guy and Salman Habib and Klaus Honscheid and Stephanie Juneau and Jean-Paul Kneib and Ofer Lahav and Dustin Lang and Alexie Leauthaud and Betta Lusso and Axel de la Macorra and Marc Manera and Paul Martini and Shude Mao and Jeffrey A. Newman and Nathalie Palanque-Delabrouille and Will J. Percival and Carlos Allende Prieto and Constance M. Rockosi and Vanina Ruhlmann-Kleider and David Schlegel and Hee-Jong Seo and Yong-Seon Song and Greg Tarle and Risa Wechsler and David Weinberg and Christophe Yeche and Ying Zu},
+      year={2019},
+      eprint={1907.10688},
+      archivePrefix={arXiv},
+      primaryClass={astro-ph.IM},
+      url={https://arxiv.org/abs/1907.10688}, 
 }
 
 @ARTICLE{DES,
@@ -235,3 +233,13 @@ @article{ABC
 doi = {10.1214/aos/1176346785},
 URL = {https://doi.org/10.1214/aos/1176346785}
 }
+
+@misc{NRE,
+      title={Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation}, 
+      author={Arnaud Delaunoy and Joeri Hermans and François Rozet and Antoine Wehenkel and Gilles Louppe},
+      year={2022},
+      eprint={2208.13624},
+      archivePrefix={arXiv},
+      primaryClass={stat.ML},
+      url={https://arxiv.org/abs/2208.13624}, 
+}

paper/paper.md

@@ -55,7 +55,7 @@ Simulation-based inference (SBI) covers a broad class of statistical techniques
 
 In the field of cosmology, SBI is of particular interest due to complexity and non-linearity of models for the expectations of non-standard summary statistics of the large-scale structure, as well as the non-Gaussian noise distributions for these statistics. The assumptions required for the complex analytic modelling of these statistics as well as the increasing dimensionality of data returned by spectroscopic and photometric galaxy surveys limits the amount of information that can be obtained on fundamental physical parameters. Therefore, the study and research into current and future statistical methods for Bayesian inference is of paramount importance for the cosmology, especially in light of current and next-generation survey missions such as DES [@Euclid], DESI [@DESI] and Euclid [@Euclid].
 
-The software we present, `sbiax`, is designed to be used by machine learning and physics researchers for running Bayesian inferences using density-estimation SBI techniques. These models can be fit easily with multi-accelerator training and inference within the code. This software - written in `jax` [@jax] - allows for seemless integration of cutting edge generative models to SBI, including continuous normalising flows [@ffjord], matched flows [@flowmatching], masked autoregressive flows [@mafs; @flowjax] and Gaussian mixture models - all of which are implemented in the code. The code features integration with the `optuna` [@optuna] hyperparameter optimisation framework which would be used to ensure consistent analyses, `blackjax` [@blackjax] for fast MCMC sampling and `equinox` [@equinox] for neural network methods. The design of `sbiax` allows for new density estimation algorithms to be trained and sampled from. 
+The software we present, `sbiax`, is designed to be used by machine learning and physics researchers for running Bayesian inferences using density-estimation SBI techniques. These models can be fit easily with multi-accelerator training and inference within the code. This software - written in `jax` [@jax] - allows for seemless integration of cutting edge generative models to SBI, including continuous normalising flows [@ffjord], matched flows [@flowmatching], masked autoregressive flows [@mafs; @flowjax] and Gaussian mixture models - all of which are implemented in the code. The code features integration with the `optuna` [@optuna] hyperparameter optimisation framework which would be used to ensure consistent analyses, `blackjax` [@blackjax] for fast MCMC sampling and `equinox` [@equinox] for neural network methods. The design of `sbiax` allows for new density estimation algorithms to be trained and sampled from, as long as they conform to a simple and typical design pattern demonstrated in `sbiax`. 
 
 Whilst excellent software packages already exist for conducting simulation-based inference (e.g. `sbi` [@sbimacke], `sbijax` [@sbidirmeier]) for some applications it is useful to have a lightweight implementation that focuses on speed, ensembling of density estimators and easily integrated MCMC sampling (e.g. for ensembles of likelihoods) - all of which is based on a lightweight and regularly maintained `jax` machine learning library such as `equinox` [@equinox]. `sbiax` depends on density estimators and compression modules - as long as log-probability and callable methods exists for these, they can be integrated seemlessly.