Diego Mesquita
@wkly_infrmtive
Machine learning, deep learning, and Bayesian methods. Assistant prof @FGVBrazil. Previously @AaltoUniversity. (Bad) Jokes are my own.
You might like
For our "Automated Assessment of Teaching Quality" project, we are looking for two PhD students: one in educational/cognitive sciences or a related field (uni-tuebingen.de/fakultaeten/wi…) and one in machine learning (uni-tuebingen.de/en/faculties/f…). Please apply and reach me out for details!
The #UAI2025 Call for Workshops is out - deadline Feb 28th! If you have an idea for a workshop on #uncertainty #AI #statsML #impreciseprobabilities #causality etc consider submitting a 2 page proposal Accepted workshops will be held on July 25 in Rio 🇧🇷 auai.org/uai2025/call_f…
Come visit us. Work beatifully led by @targb4, who will soon defend his PhD.
Are you using Bayesian models to infer discrete parameters, like phylogenetic trees, but don't want to keep growing your dataset as new observations arrive? Come join me and @wkly_infrmtive to learn more at the #NeurIPS2024 11am poster session in the East Exhibit Hall #4010.
The 41st Conference on #Uncertainty in #AI will be held in Rio de Janeiro 🇧🇷, July 21-25! The CfP is out 👉auai.org/uai2025/call_f… 🚨 Feb 10: Paper submission 🗣️ Apr 3-10: rebuttal period 🎉/💀 May 6: Author notification #UAI2025 #ML #stats #learning #reasoning #uncertainty
📢 Advance publication in Bayesian Analysis projecteuclid.org/journals/bayes…
I am looking for highly motivated post-docs to work on fundamental AI research. Pay is competitive (>=) compared to any Brazilian institution. Solid math/stats/theoretical CS background greatly appreciated. Instructions on my personal page.
Paper X (under review) and Y (published) have at least a common author. X openly states results from Y are misleading and cannot be reproduced. Is this ok?
PhD student watching the PI present a technically impossible solution to a collaborator
Our work at #ICML2024 enables one-shot Bayesian federated/parallel inference over discrete spaces (e.g., graphs). In @willieneis's embarrassingly style, we use @folinoid 's GFlowNets to learn local posteriors and combine them using our *aggregating balance condition*.…
ML Twitter seems excessively confrontational these last few days
Build what you need and use what you build. This is a core philosophy of my research. It shifts the focus away from publishing “papers” to what really matters — impact. This thread unpacks why I think this is a successful approach to science. 1/10 Or see: perceiving-systems.blog/en/post/build-…
GNN-based link prediction is typically miscalibrated. Read our preprint for further discussion on the issue and the first calibration method explicitly designed for the task. @amaurihsouza @samikaski arxiv.org/abs/2403.04605
I am looking for a post-doc to work with me on ML in Rio. Possible topics include generative models, geometric deep learning, probabilistic methods, federated ML, privacy-preserving ML, etc. Salary ~10kBRL. E-mail/msg me if interested.
📢 Early bird call: Soon to open is an exciting opportunity for PhD research 🎓 in the CS dept @csmcr ✨ U of Manchester @OfficialUoM 👌 supervised by me and @SamiKaski. To work at the forefront of statistical theory and methods for distribution shifts 🤓 DM me for enquiring!
We're hosting the Tropical ProbAI school @FGV Jan 29-Feb 2, in Rio de Janeiro. Good news: applications are still open. This year, we'll have lectures & talks from the exceptional @vmansinghka @D_Bouchacourt @adelehr @HelgeLangseth @ZennaTavares + more tropical.probabilistic.ai
we need less crappy journals and more high quality conferences
United States Trends
- 1. #HardRockBet 3,639 posts
- 2. #AskFFT 1,014 posts
- 3. Arsenal 237K posts
- 4. Tottenham 74.6K posts
- 5. Mason Rudolph 2,586 posts
- 6. Merino 16.2K posts
- 7. Thomas Frank 3,488 posts
- 8. #ARSTOT 10.7K posts
- 9. Klay 41.2K posts
- 10. #COYG 5,636 posts
- 11. Trossard 11.6K posts
- 12. Great for 60 N/A
- 13. Aaron Rodgers 5,628 posts
- 14. Good Sunday 83.9K posts
- 15. Emanuel Wilson N/A
- 16. Sean Tucker 1,011 posts
- 17. Full PPR 1,451 posts
- 18. #sundayvibes 7,541 posts
- 19. Cornbread 2,024 posts
- 20. NFL Sunday 7,286 posts
Something went wrong.
Something went wrong.