Christian A. Naesseth

@naesseth
344 Followers
166 Following
67 Posts
Researcher interested in approximate inference, causality and artificial intelligence as well as their application to the sciences. Assistant professor in the Amsterdam Machine Learning Lab at the University of Amsterdam.
Websitehttps://naesseth.github.io/
Scholarhttps://scholar.google.com/citations?user=GQ6rOssAAAAJ
Twitterhttps://twitter.com/chris_naesseth
Show threadChristian A. NaessethMay 23, 2023

Only 3 days left to submit to the #AABI2023 fast-track call for papers previously accepted at top ML conferences and journals within 2023. (CfP: http://approximateinference.org/call/index.html)

The track is non-archival but gives authors a chance to present at AABI in Hawaii 🌴🌴!

#ML #Bayes #ICML2023 #AABI2023 #GenerativeAI #AI

Approximate Inference - Call for Papers

Christian A. NaessethMay 16, 2023

The 5th Symposium on Advances in Approximate Bayesian Inference welcomes your accepted ML journal & conf papers via fast-track! Come present your work at the poster session.

OpenReview: https://openreview.net/group?id=approximateinference.org/AABI/2023/Symposium_Fast_Track

CfP: http://approximateinference.org/call/index.html
#MachineLearning #Bayes #ICML2023 #AABI

AABI 2023 Symposium Fast Track

Welcome to the OpenReview homepage for AABI 2023 Symposium Fast Track

OpenReview
Show threadChristian A. NaessethMay 1, 2023
It turns out that when using Trajectory Balance to optimise the GFN it coincides with standard variational inference (VI) for the generative and reverse models! This connection allows us to leverage VI-improvements developed also for GFNs. See the paper for more details.
Show threadChristian A. NaessethMay 1, 2023
GFNs are generative models that uses auxiliary variables to recursively construct a distribution on the data space s_n to model a reward function R(s_n). For training, a reverse model of the generative models is constructed to enable optimisation.
Christian A. NaessethMay 1, 2023

New work by Heiko, Fredrik, Jan-Willem and myself interpreting Generative Flow Networks (GFN) as generative models trained by variational inference!

#TMLR #GenerativeAI #GFN #MachineLearning

https://openreview.net/forum?id=AZ4GobeSLq

A Variational Perspective on Generative Flow Networks

Generative flow networks (GFNs) are a class of probabilistic models for sequential sampling of composite objects, proportional to a target distribution that is defined in terms of an energy...

OpenReview
Christian A. NaessethMar 13, 2023

Advances on Approximate Bayesian Inference (AABI 2023) is accepting nominations for reviewers, invited speakers, panelist, and future organizing committee members. Let us know who you'd like to hear from! Self-nominations accepted.

https://forms.gle/gBZUQsmXgNFmLCm2A

More information about the symposium can be found on our homepage: http://approximateinference.org/

#aabi #bayes #approximateinference #machinelearning #icml2023

AABI 2023 Nominations

Please use this form to suggest members of the research community as reviewers, invited speakers, panelists, and organizing committee. Self-nominations are accepted.

Google Docs
Christian A. NaessethFeb 28, 2023

Im very excited to announce that everyone's favourite Bayesian symposium is back for 2023!🚀🚀
The 5th Symposium on Advances in Approximate Bayesian Inference (AABI) will take place in 🏖️Honolulu Hawaii🌴, Sunday July 23rd, Co-Located with ICML!

Website: http://approximateinference.org
#aabi #machinelearning #bayes #icml

Approximate Inference

Christian A. NaessethFeb 21, 2023
Junpeng Lao 🏂Feb 20, 2023
Looks like the program for #BayesComp2023 is out (bayescomp2023.com/)! I am very excited to visit Levi, #Finland in March! Super excited to:
- meeting fellow #Bayesians @avehtari, @sethaxen
- presenting short talk on functional programming for Bayesian workflow with #tensorflow_probability and #blackjax
- skiing some Finland powder
Christian A. NaessethDec 22, 2022
Emtiyaz KhanDec 22, 2022

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.

Christian A. NaessethDec 20, 2022
Pierre JacobDec 17, 2022
14th international conference on Monte Carlo methods and Applications will be in Paris, June 26-30 2023, https://mcm2023.sciencesconf.org/
14th International Conference on Monte Carlo Methods and Applications - Sciencesconf.org