[PRE REVIEW]: SBGM: Score-based diffusion models in JAX

[editorialbot]

Submitting author: @homerjed (Jed Homer)
Repository: https://github.com/homerjed/sbgm
Branch with paper.md (empty if default branch):
Version: 0.0.18
Editor: @mahfuz05062
Reviewers: Pending
Managing EiC: Chris Vernon

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/d08492d581f38316cfa6faa3b3377421"><img src="https://joss.theoj.org/papers/d08492d581f38316cfa6faa3b3377421/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/d08492d581f38316cfa6faa3b3377421/status.svg)](https://joss.theoj.org/papers/d08492d581f38316cfa6faa3b3377421)

Author instructions

Thanks for submitting your paper to JOSS @homerjed. Currently, there isn't a JOSS editor assigned to your paper.

@homerjed if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). You can search the list of people that have already agreed to review and may be suitable for this submission.

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

[editorialbot]

Hello human, I'm @editorialbot, a robot that can help you with some common editorial tasks.

For a list of things I can do to help you, just type:

@editorialbot commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@editorialbot generate pdf

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.98  T=0.04 s (1029.3 files/s, 136688.0 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
Python                          35            804            851           3026
TeX                              1             33              0            283
Markdown                         2            106             17            213
YAML                             3             20              8            165
Jupyter Notebook                 2              0            283            116
TOML                             1              3              0             47
Text                             1              0              0              1
-------------------------------------------------------------------------------
SUM:                            45            966           1159           3851
-------------------------------------------------------------------------------

Commit count by author:

    69	homerjed
    35	Jed.Homer

[editorialbot]

Paper file info:

📄 Wordcount for paper.md is 1894

✅ The paper includes a Statement of need section

[editorialbot]

License info:

✅ License found: MIT License (Valid open source OSI approved license)

[editorialbot]

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

✅ OK DOIs

- 10.1073/pnas.1912789117 is OK
- 10.1093/mnras/stad432 is OK
- 10.1093/mnras/stac064 is OK
- 10.1051/0004-6361/202243054 is OK

🟡 SKIP DOIs

- No DOI given, and none found for title: Deep Unsupervised Learning using Nonequilibrium Th...
- No DOI given, and none found for title: Denoising Diffusion Probabilistic Models
- No DOI given, and none found for title: Variational Bayesian Imaging with an Efficient Sur...
- No DOI given, and none found for title: Solving Inverse Problems in Medical Imaging with S...
- No DOI given, and none found for title: Conditional Image Generation with Score-Based Diff...
- No DOI given, and none found for title: On Neural Differential Equations
- No DOI given, and none found for title: Score-Based Generative Modeling through Stochastic...
- No DOI given, and none found for title: Maximum Likelihood Training of Score-Based Diffusi...
- No DOI given, and none found for title: FFJORD: Free-form Continuous Dynamics for Scalable...
- No DOI given, and none found for title: Neural Ordinary Differential Equations
- No DOI given, and none found for title: Consistent Diffusion Meets Tweedie: Training Exact...
- No DOI given, and none found for title: JAX: composable transformations of Python+NumPy pr...
- No DOI given, and none found for title: Equinox: neural networks in JAX via callable PyTre...
- No DOI given, and none found for title: The DeepMind JAX Ecosystem
- No DOI given, and none found for title: U-Net: Convolutional Networks for Biomedical Image...
- No DOI given, and none found for title: High-Resolution Image Synthesis with Latent Diffus...
- No DOI given, and none found for title: Generative Adversarial Networks
- No DOI given, and none found for title: Auto-Encoding Variational Bayes
- No DOI given, and none found for title: Normalizing Flows for Probabilistic Modeling and I...
- No DOI given, and none found for title: BlackJAX: Composable Bayesian inference in JAX
- No DOI given, and none found for title: Variational Diffusion Models
- No DOI given, and none found for title: Conditional Image Generation with Score-Based Diff...
- No DOI given, and none found for title: MLP-Mixer: An all-MLP Architecture for Vision

❌ MISSING DOIs

- 10.1109/iccv51070.2023.00965 may be a valid DOI for title: Score-Based Diffusion Models as Principled Priors ...
- 10.1109/cvpr52729.2023.00587 may be a valid DOI for title: Parallel Diffusion Models of Operator and Image fo...
- 10.1109/cvpr.2016.90 may be a valid DOI for title: Deep Residual Learning for Image Recognition
- 10.1109/iccv51070.2023.00387 may be a valid DOI for title: Scalable Diffusion Models with Transformers

❌ INVALID DOIs

- None

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[editorialbot]

Five most similar historical JOSS papers:

flowMC: Normalizing flow enhanced sampling package for probabilistic inference in JAX
Submitting author: @kazewong
Handling editor: @rkurchin (Active)
Reviewers: @matt-graham, @Daniel-Dodd
Similarity score: 0.6562

sbi: A toolkit for simulation-based inference
Submitting author: @janfb
Handling editor: @dfm (Active)
Reviewers: @EiffL, @cranmer
Similarity score: 0.6510

BlackBIRDS: Black-Box Inference foR Differentiable Simulators
Submitting author: @arnauqb
Handling editor: @rkurchin (Active)
Reviewers: @rajeshrinet, @marvinschmitt
Similarity score: 0.6506

PyVBMC: Efficient Bayesian inference in Python
Submitting author: @Bobby-Huggins
Handling editor: @rkurchin (Active)
Reviewers: @matt-graham, @isdanni
Similarity score: 0.6502

Disimpy: A massively parallel Monte Carlo simulator for generating diffusion-weighted MRI data in Python
Submitting author: @kerkelae
Handling editor: @Kevin-Mattheus-Moerman (Active)
Reviewers: @DARSakthi, @grlee77, @ritagnunes
Similarity score: 0.6478

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before considering asking the reviewers of these papers to review again for JOSS.

[crvernon]

👋 @homerjed - while I am finding a topic editor to assign to this submission, please reduce the word count of your paper to 1000 words or less. Thank you!

[homerjed]

👋 @crvernon, thank you. I've shortened it to ~1,190 by my count (not sure how to count with your automatic method without spamming notifications). I'll try to reduce more and find two reviewers.

[arnauqb]

Hi @homerjed. Thank you for considering me as a potential reviewer. Unfortunately, I do not have the bandwidth to review your package in the next few months. Good luck!

[crvernon]

@editorialbot invite @mahfuz05062 as editor

👋 @mahfuz05062 can you take this one on as editor?

[editorialbot]

Invitation to edit this submission sent!

[mahfuz05062]

@editorialbot assign @mahfuz05062 as editor

[editorialbot]

Assigned! @mahfuz05062 is now the editor

[mahfuz05062]

Hi @homerjed, do you have any suggestions for potential reviewers? If so, please mention them here (without tagging them with an @). You can search the list of people who have already agreed to review and may be suitable for this submission. I will then contact the potential reviewers to finalize the reviewers for this submission.

[mahfuz05062]

Hi @homerjed, do you have any suggestions for potential reviewers? If so, please mention them here (without tagging them with an @). You can search the list of people who have already agreed to review and may be suitable for this submission. I will then contact the potential reviewers to finalize the reviewers for this submission.

Hi @homerjed, checking in again if you had any input on this?

[homerjed]

Hi @mahfuz05062, I've been doing a lot of teaching the last weeks, I'm giving myself till the end of this week to locate some potential reviewers. Sorry for the delay!