Do you want expressive mixture models that can subtract probability mass? you can square circuits! But by doing so we can also lose expressiveness 🚨 We introduce sum of squares 🆘 PCs to overcome this limitation. 🆘 PCs also explain why complex parameters boost performance!

Isabel Valera pointing out how many open questions there are in causal and ethical machine learning 🤩. “We can’t have a technology whose capabilities advance fast without similar speed in advances in responsible ai”. #DLI2024 #Indaba2024 #xamxamle 🌍

#CKIWFest is starting now at School of Informatics, The University of Edinburgh The University of Edinburgh a 2 day workshop with talks from stars in probabilistic #ML whose career intersected with Chris Williams, who is retiring. Lineup is at 📜workshops.inf.ed.ac.uk/ml/ckiwfest/

👋I am on the academic job market, looking for tenure-track positions. I work on machine learning, decision making, and social aspects of AI. Let's get in touch if your institution is hiring! 💻stsirtsis.github.io 😀Shares are very much appreciated!

and congratulations to Dr. Filippo Corponi who successfully passed his viva, examined by Paolo Ossola and Kia Nazarpour Filippo's thesis is a wonderful bridge between #ML #AI and clinical practice in psychiatry for mood disorders with wearable!

🚨 A postdoc position in rational machine learning in our group @CISPA. If you want to collaborate with us to create more rational, efficient, and reliable machine learning systems, don't hesitate to reach out. 📄 tinyurl.com/2jksdehr RT Appreciated 🙏

many of the recent successes in #AI #ML are due to #structured low-rank representations! but...What's the connection between #lowrank adapters, #tensor networks, #polynomials and #circuits? join our AAAI workshop to know the answer! 👇👇👇 april-tools.github.io/colorai/

great opportunity to do a #PhD in #Europe in #ML #AI 🚨🚨🚨 I'll hire 2 students via #ELLIS this year, reach out if you want to do research in: - #reliable and #efficient ML in the wild - scalable #neurosymbolic #nesy AI - #lowrank representations - #tractable inference 🚨🚨🚨

We learn more expressive mixture models that can subtract probability density by squaring them 🚨We show squaring can reduce expressiveness To tackle this we build sum of squares circuits🆘 🚀We explain why complex parameters help, and show an expressiveness hierarchy around🆘

Now hiring: Twelve (!) PhD students to start in fall 2025, for research on combining neural and symbolic/interpretable models of language, vision, and action. Work with world-class advisors at Universität Saarland, MPI Informatics, MPI-SWS, @CISPA, DFKI. Details: neuroexplicit.org/jobs

Isabel is an incredible person and supervisor! Consider applying if you want to do great research in ML 😉

I’ll be attending #NeurIPS2024, where I’ll present our spotlight: Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits (PICs). TL;DR: We learn continuous hierarchical mixtures as DAG-shaped PICs, and scale them using neural functional sharing techniques.

PLS SHARE: I'm hiring a PhD student to work on ML theory, to begin in Fall 2025. Topics include: generalization bounds & statistical inference via online prediction, representation learning via optimal transport, sequential decision making... More info: cs.bme.hu/~gergo/jobs.ht…

Reminder: the tweets of my advisors do not necessarily represent the views of their employees

I am recruiting a PhD student to being in September 2025, through the ELLIS call for PhD students: ellis.eu/news/ellis-phd… (deadline Nov 15th)

I am flattered to announce that I have become a top² reviewer at NeurIPS Conference

I read Painful intelligence when it came out, and many of its insights still live rent-free on my mind to this day. Highly recommended!

Less than two weeks to submit your papers on: 📈 #lowrank adapters and #factorizations 🧊 #tensor networks 🔌 probabilistic #circuits 🎓 #theory of factorizations to the first workshop on connecting them in #AI #ML at AAAI please share! 🔁 👇👇👇 april-tools.github.io/colorai/