Skip to content
Archive of entries posted by

Custom Distribution Solutions

I (Aki) recently made a case study that demonstrates how to implement user defined probability functions in Stan language (case study, git repo). As an example I use the generalized Pareto distribution (GPD) to model extreme values of geomagnetic storm data from the World Data Center for Geomagnetism. Stan has had support for user defined […]

Postdoc in Finland and NY to work on probabilistic inference and Stan!

I (Aki) got 2 year funding to hire a postdoc to work on validation of probabilistic inference approaches and model selection in Stan. Work would be done with Stan team in Aalto, Helsinki and Columbia, New York. We probably have PhD positions, too. The funding is part of the joint project with Antti Honkela and […]

Tenure-Track or Tenured Prof. in Machine Learning in Aalto, Finland

This job advertisement for a position in Aalto, Finland, is by Aki We are looking for a professor to either further strengthen our strong research fields, with keywords including statistical machine learning, probabilistic modelling, Bayesian inference, kernel methods, computational statistics, or complementing them with deep learning. Collaboration with other fields is welcome, with local opportunities […]

Stacking, pseudo-BMA, and AIC type weights for combining Bayesian predictive distributions

This post is by Aki. We have often been asked in the Stan user forum how to do model combination for Stan models. Bayesian model averaging (BMA) by computing marginal likelihoods is challenging in theory and even more challenging in practice using only the MCMC samples obtained from the full model posteriors. Some users have […]

Research fellow, postdoc, and PhD positions in probabilistic modeling and machine learning in Finland

Probabilistic modeling and machine learning are strong in Finland. Now is your opportunity to join us in this cool country! There are several postdoc and research fellow positions open in probabilistic machine learning in Aalto University and University of Helsinki (deadline Marh 19). Some of the topics are related also to probabilistic programming and Stan […]

Practical Bayesian model evaluation in Stan and rstanarm using leave-one-out cross-validation

Our (Aki, Andrew and Jonah) paper Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC was recently published in Statistics and Computing. In the paper we show why it’s better to use LOO instead of WAIC for model evaluation how to compute LOO quickly and reliably using the full posterior sample how Pareto smoothing importance […]

Tenure Track Professor in Machine Learning, Aalto University, Finland

Posted by Aki. I promise that next time I’ll post something else than a job advertisement, but before that here’s another great opportunity to join Aalto Univeristy where I work, too. “We are looking for a professor to either further strengthen our strong research fields, with keywords including statistical machine learning, probabilistic modelling, Bayesian inference, […]

Several postdoc positions in probabilistic modeling and machine learning in Aalto, Helsinki

This post is by Aki In addition to the postdoc position I advertised recently, now Aalto University and University of Helsinki have 20 more open postdoc and research fellow positions. Many of the positions are in probabilistic models and machine learning. You could work with me (I’m also part of HIIT), but I can also […]

R demos for BDA3

Last year we published some Matlab/Octave and Python demos for BDA3. During the summer my student Markus Paasiniemi ported these demos to R. New R BDA3 demos are now available in github. We hope these are helpful for someone. They are now just R code, although R Markdown would be cool. Btw. we are expecting […]

Postdoc in Finland with Aki

I’m looking for a postdoc to work with me at Aalto University, Finland. The person hired will participate in research on Gaussian processes, functional constraints, big data, approximative Bayesian inference, model selection and assessment, deep learning, and survival analysis models (e.g. cardiovascular diseases and cancer). Methods will be implemented mostly in GPy and Stan. The […]

Postdoctoral Researcher and Research Fellow positions in Computer Science in Helsinki, Finland

There are several PostDoc positions open in Aalto University and University of Helsinki related to statistical modeling, Bayesian inference, probabilistic programming (including Stan) and machine learning. There is also possibility to collaborate with me :) See a detailed list of the research areas and the full call text. The deadline is April 1, 2016. My […]

Stan – The Bayesian Data Scientist’s Best Friend

My friend Juuso Parkkinen has interesting Stan related blog, which is worth following. The above cool animation is from today’s post discussing the updated results of using Stan to model apartment prices in Finland. Few weeks ago Juuso also blogged about a probabilistic programming seminar in Finland with a title Stan – The Bayesian Data […]

Phd positions in Probabilistic Machine Learning at #AaltoPML group Finland

There are PhD positions in our Probabilistic Machine Learning group at Aalto, Finland, and altogether 15 positions in Helsinki ICT network. Apply here The most interesting topic in the call is supervised by Prof. Samuel Kaski at AaltoPML (and you may collaborate with me too :) We are looking for PhD candidates interested in probabilistic […]

Summer internship positions for undergraduate students with Aki

There are couple cool summer internship positions for undergraduate students (BSc level) in Probabilistic Machine Learning group at Aalto (Finland) with me (Aki) and Samuel Kaski. Possible research topics are related to Bayesian inference, machine learning, Stan, disease risk prediction, personalised medicine, computational biology, contextual information retrieval, information visualization, etc. Application deadline 18 February. See more […]

Pareto smoothed importance sampling and infinite variance (2nd ed)

This post is by Aki Last week Xi’an blogged about an arXiv paper by Chatterjee and Diaconis which considers the proper sample size in an importance sampling setting with infinite variance. I commented Xi’an’s posting and the end result was my guest blog posting in Xi’an’s og. I made an additional figure below to summarise […]

Matlab/Octave and Python demos for BDA3

My Bayesian Data Analysis course at Aalto University started today with a record number of 84 registered students! In my course I have used some Matlab/Octave demos for several years. This summer Tuomas Sivula translated most of them to Python and Python notebook. Both Matlab/Octave and Python demos are now available at Github in hope they […]

Are you ready to go fishing in the data lake?

While Andrew is trying to get someone to make a t-shirt design “Gone fishing”, someone else thinks fishing is one of the “big data trends in 2015”. This advertisement by some company keeps re-appearing in my twitter feed.

Comparison of Bayesian predictive methods for model selection

This post is by Aki We mention the problem of bias induced by model selection in A survey of Bayesian predictive methods for model assessment, selection and comparison, in Understanding predictive information criteria for Bayesian models, and in BDA3 Chapter 7, but we haven’t had a good answer how to avoid that problem (except by […]

Cross-validation, LOO and WAIC for time series

This post is by Aki. Jonah asked in Stan users mailing list Suppose we have J groups and T time periods, so y[t,j] is the observed value of y at time t for group j. (We also have predictors x[t,j].) I’m wondering if WAIC is appropriate in this scenario assuming that our interest in predictive accuracy is for […]

Students don’t know what’s best for their own learning

[This post is by Aki] This is my first blog posting. Arthur Poropat at Griffith University has a great posting Students don’t know what’s best for their own learning about two recent studies which came to the same conclusion: university students evaluate their teachers more positively when they learn less. My favorite part is That is why many […]