🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We present Truncated Marginal Neural Ratio Estimation, a simulation-based inference method which excels at efficient and testable posterior approximation. It works even when the likelihood is intractable! 1/5

Grateful to the U.S. National Science Foundation SCALE MoDL program for awarding us $1M to study the role of symmetry and representation theory in deep learning. Excited to work with Rose Yu at UCSD CSE and Jan-Willem van de Meent at Khoury College of Computer Sciences (and maybe you soon) for the next 3 years! @NSF_MPS #DMSFunded

I'm delighted that Nested Variational Inference will appear at NeurIPS 2021! This paper got in on the first round, but many papers from our lab have gone through multiple rounds of review (our record is 5 rounds). Keep your head up if your submission did not get in this time!

To celebrate the start of the PROBPROG conference today (probprog.cc), we have put the next iteration of our book on probabilistic programming online: arxiv.org/abs/1809.10756. [1/]

Excited to present my work with Hao Wu (Hao Wu), Babak Esmaeili (Babak Esmaeili), and Jan-Willem van de Meent (Jan-Willem van de Meent) on Nested Variational Inference at #NeurIPS2021 today. Come and join us in poster session 1 at spot C0.

Happy to announce that our paper "Self-Supervised Inference in State-Space Models" got accepted to ICLR2022! Among others, we show that we can obtain performance similar to Satorras et al., 2019 without clean data. Víctor Garcia Satorras Zeynep Akata Max Welling arxiv.org/abs/2107.13349

🧑‍🎓 PhD opportunity in Machine Learning I am recruiting a PhD student to work with me at UvA AMLab in Amsterdam on topics such as approximate statistical inference, causal inference, generalization, etc. Deadline April 10 vacatures.uva.nl/UvA/job/PhD-Po…

Molecule Generation in 3D with Equivariant Diffusion (arxiv.org/abs/2203.17003). Very happy to share this project (the last of my PhD woohoo 🥳) and a super nice collab with Víctor Garcia Satorras @ClementVignac (equal contrib shared among three of us) and of course Max Welling

Time to start thinking about that AISTATS submission! :) Abstract deadline: Thu Oct 6 AoE Paper deadline: Thu Oct 13 AoE Conference will be hybrid, in-person location in the US.

New work by Heiko Zimmermann 🦋 [email protected] Fredrik Lindsten Jan-Willem van de Meent and myself interpreting Generative Flow Networks (GFN) as generative models trained by variational inference! #TMLR #GenerativeAI #GFN #MachineLearning openreview.net/forum?id=AZ4Go…

VISA: Variational Inference with Sequential Sample-Average Approximations. arxiv.org/abs/2403.09429

We've recently released Coix, a JAX-based framework designed for composing probabilistic programs and performing inference on them. Let's make Sequential Monte Carlo easy to apply. Tutorials are here coix.readthedocs.io/en/latest/ Joint work with Heiko Zimmermann 🦋 [email protected] Tuan Anh Le Sharad Vikram

Go for Gram Workshop at #ICML2024 !!

📍I'll be AABI this Sunday and ICML Conference next week. If you're interested in diffusion models, feel free to reach out! 👨‍💼I hope to see you on Tuesday, July 23rd, in Hall C from 4-9 PM at Booth #712 to discuss Neural Diffusion Models!

Jakub Tomczak AABI Gram Workshop ICML Conference Thank you for your kind words 😭🙏

Happening now! Find us at #712 in Hall C.

I’m hiring a postdoc to work with me on exciting projects in generative modelling (AI) and/or uncertainty quantification. You'll be part of a great team, embedded in UvA AMLab and the UvA-Bosch Delta Lab. Apply here: vacatures.uva.nl/UvA/job/Postdo… RT appreciated! #ML #GenAI

2. VISA: Variational Inference with Sequential Sample-Average Approximations by by Heiko Zimmermann 🦋 [email protected], Christian A. Naesseth, and myself 🪪neurips.cc/virtual/2024/p… 📷arxiv.org/abs/2403.09429

I'm gonna be at #Neurips this week to present our work on variational inference with sequential sample-average approximations (neurips.cc/virtual/2024...). I'm also on the job market! Happy to chat all things probabilistic modeling and inference!