antonio vergari

@nolovedeeplearning
2 Followers
112 Following
212 Posts
human being | assistant prof in #ML #AI @ancAtEd
@EdinburghUni | prev @UCLA @MPI_IS | #probabilistic #inference #tractable #generative #neuro #symbolic | he/him
websitenolovedeeplearning.com

About to fly to #Germany for a short #research tour of Saarland University, Max Planck Institute for Intelligent Systems, University of Tübingen, University of Stuttgart and TU Darmstadt!

Super happy to meet old friends and colleagues @IValeraM Steffen Staab @mniepert @bschoelkopf @PhilippHennig @Matthiasbetghe @kerstingAIML @javaloyML and more!

I made an example of how implementations of user defined probability functions in Stan can be tested in the generated quantities block. This is a much faster and easier approach to see implementation errors than by running MCMC.

See more in Stan Discourse post https://discourse.mc-stan.org/t/testing-user-defined-probability-function-implementations-in-stan-generated-quantities/29907

#Stan #MCMC #Bayes

Testing user defined probability function implementations in Stan generated quantities

This post is inspired by Stan Slack discussion about implementing user defined probability functions and related to my old case study on implementing generalized Pareto distribution. In that case study, I implemented tests to check the correctness of the probability function implementations in R. Now that we have integrate_1d in Stan, we can make several tests also in generated quantities block. The idea is that we can test the user defined probability density function implementations quickly a...

The Stan Forums
@trappmartin @mattodon Some probabilistic programming languages like ProbLog and Dice compile into probabilistic circuits for inference!
@mattodon Also I heard Robert (@rope ), Antonio (@nolovedeeplearning), and Guy (@guy) gave a tutorial at NeurIPS. I would definitely recommend this. During my PhD I was very privileged to work with them and learned a lot.

I will have an open #internship position @AaltoUniversity on #probabilistic #circuits.

The internship will be within Aalto's #AScI program, which is an excellent opportunity! See project 4116 in the announcement below.

🔗 https://www.aalto.fi/en/aalto-science-institute-asci/asci-international-summer-research-program-2023-project-list

#MachineLearning

AScI international summer research program: 2023 project list | Aalto University

Here are AScI's research projects for summer 2023.

I will be opening a new post-doc position in our group with a potential starting date late summer or Sept. 2023. If you are interested, please get in touch by sending your CV at jobs-abi-riken-aip [at] googlegroups dot com.

Boost appreciated! Help me spread the word.

We are organizing an exciting workshop on the intersection of deep generative modelling and neurosymbolic learning at #ICLR2023 💎!

The call for papers is out now: https://nesygems.github.io/callforpapers/
Submission deadline: 3rd of February 2023

#neurosymbolic #generativemodels

Call for papers

We are organizing a very exciting workshop on the intersection of Neurosymbolic and Generative Modeling. The workshop is hybird, and is scheduled to take place jointly with ICLR 2023 in Kigali, Rwanda, either the 4th or 5th of May.

NeSy-GeMs workshop @ ICLR 2023

RT @[email protected]

Super excited about hosting this workshop on multimodal representation learning at #ICLR2023! Is embedding multimodal data a waste of modelling capacity or a way to learn more generalisable representation? Submit your work and join our discussion! https://twitter.com/mrlworkshop/status/1604794318866518016

🐦🔗: https://twitter.com/YugeTen/status/1605164219523301377

Multimodal Representation Learning @ ICLR23 on Twitter

“Is having multiple modalities a blessing or a curse? What is a good representation? Let's find out together! We are proud to announce the 1st hybrid workshop on Multimodal Representation Learning at #ICLR2023 (@iclr_conf) 🚀 More info: https://t.co/EvoMrhi4VN”

Twitter

Great news! Our hybrid workshop on Neurosymbolic Generative Models was accepted at ICLR 2023 🎉🎉🎉

More details on https://nesygems.github.io/

Co-organisers: @EmilevanKrieken, Halley Young, Disha Shrivastava, @jmtomczak and Kevin Ellis.

#neurosymbolic #generativemodelling #ML #AI

NeSy-GeMs workshop @ ICLR 2023

We are organizing a very exciting workshop on the intersection of Neurosymbolic and Generative Modeling. The workshop is hybird, and is scheduled to take place jointly with ICLR 2023 in Kigali, Rwanda, either the 4th or 5th of May.

NeSy-GeMs workshop @ ICLR 2023
@MPDL welcome!