Call for Papers

We invite submissions to the 7th Symposium on Advances in Approximate Bayesian Inference, and welcome paper submissions and extended abstracts on the development, analysis, or application of probabilistic methods in machine learning.

The 7th Symposium on Advances in Approximate Bayesian Inference (AABI) will have an expanded scope and will be focused on the development, analysis, and application of probabilistic machine learning methods broadly construed. In line with this expanded focus, we particularly welcome submissions that explore connections between probabilistic machine learning and other fields such as deep learning, natural language processing, active learning, reinforcement learning, compression, AI safety, AI for scientific discovery, and causal inference. We also encourage contributions that advance the foundations of probabilistic machine learning and machine learning theory.

We are delighted to continue the archival AABI proceedings track, where full research papers will be subjected to a rigorous peer-review and published in proceedings of the symposium under the title Advances in Approximate Bayesian Inference 2025.

Key Dates

Proceedings and Workshop Tracks

• Submission deadline (Proceedings and Workshop Tracks): 7 February 2025 (11:59pm AoE)
• Reviews released (Proceedings Track): 28 February 2025
• Author rebuttal due (Proceedings Track): 7 March 2025 (11:59pm AoE)
• Acceptance notification (Proceedings, Workshop): 18 March 2025
• Camera-ready for accepted submissions: 20 April 2025
• Symposium date: 29 April 2025

Fast Track

• Submission deadline (‘Early’ Fast Track): 14 February 2025 (11:59pm AoE)
• Acceptance notification (‘Early’ Fast Track): 18 February 2025
• Submission deadline (‘Late’ Fast Track): 14 March 2025 (11:59pm AoE)
• Acceptance notification (‘Late’ Fast Track): 18 March 2025

Paper Submission

This year we will run three submission tracks:

• a Proceedings Track, for full research papers of up to 12 content pages,
• a Workshop Track, for extended abstracts of 3-6 content pages, and
• a Fast Track, for recently published papers.

Acknowledgements, references, and appendices do not contribute to the page limits.

Proceedings Track

The proceedings track is AABI’s archival research paper track. Submissions will go through a rigorous double-blind open peer-review process. All accepted papers will be presented at the symposium as contributed talks and/or posters and will all be published in the proceedings.

A submission is no longer than 12 pages in PDF format using the AABI PMLR one-column style (template). For questions and troubleshooting, visit CTAN.

Author names need to be anonymized and may not contain any information that can break anonymity. References may extend as far as needed beyond the page limit. Submissions may include a supplement, but reviewers are not required to read any supplementary material. Preprints must not be explicitly identified as AABI submissions, and we recommend that authors avoid advertising the material during the review process.

The review process will be a double-blind open review. After the initial reviews are released (28 February 2025), there will be one (1) week of author-reviewer discussion. The final decisions will then be released on 18 March 2025.

Proceedings track papers published at AABI will be indexed in the Proceedings of Machine Learning Research through the Journal of Machine Learning Research under the series name Advances in Approximate Bayesian Inference.

Dual submission policy: Submitted manuscripts should not have been previously published in the proceedings of a conference or in a journal, nor should they be under consideration for publication at another conference or journal at any point during the AABI review process. Extended abstracts and/or preprints (such as arXiv) in non-archival venues will not be considered concurrent submissions.

To submit proceedings track papers, please use the OpenReview submission link (coming soon).

Workshop Track

A workshop track submission should take the form of an extended abstract of 3-6 pages in PDF format. Submissions may use the AABI PMLR one-column style (template) or the format of any other workshop so long as the length is not more than 6 pages. For questions and troubleshooting, visit CTAN.

The review process will be double-blind. Author names need to be anonymized and references may extend as far as needed beyond the 6-page limit. Submissions may include a supplement/appendix, but reviewers are not required to read any supplementary material. Final decisions and reviews will be released on 18 March 2025.

All accepted submissions will be presented in person as posters. Note that the workshop track is non-archival.

Dual submission policy: If a paper has previously appeared in a journal, workshop, or conference, it should be extended in order to be accepted at the AABI 2025. If a paper is currently under review, it can still be submitted to the AABI workshop track.

To submit workshop track papers, please use the OpenReview submission link (coming soon).

Fast Track

We also invite researchers to present papers on the development, analysis, or application of approximate Bayesian inference that have previously been accepted at major machine learning conferences and journals – such as ICLR and AISTATS, as well as JMLR and TMLR – since AABI 2024. These papers should be formatted according to the camera-ready standards of their respective venues. Author names do not need to be anonymized. AABI Fast Track is non-archival and does not have proceedings to avoid conflict with other venues’ double submission policies.

Papers accepted within this modality will be presented in person as posters. These papers will not appear on the AABI website.

To submit fast track papers, please use this submission link.

Please note that we have two Fast Track deadlines:

• ‘Early’ — 14 February 2025 (11:59pm AoE)
• ‘Late’ — 14 March 2025 (11:59pm AoE)

Papers submitted before the ‘early’ deadline will receive acceptance notifications on 18 February 2025. Papers submitted after this deadline but before the ‘late’ deadline will receive acceptance notifications on 18 March 2025.