Aki Vehtari
Department of Computer Science

Aki Vehtari

Professor (Associate Professor)

Contact information

Email
[email protected]
Postal address
Aalto SCI Computer Science Konemiehentie 2
Mobile phone
+358405333747
Full researcher profile
https://research.aalto.fi/...

Description

I'm co-leader of the Probabilistic Machine Learning Group at Aalto. We develop new methods for probabilistic modeling, Bayesian inference and machine learning. Our current focuses are in particular probabilistic programming, learning from multiple data sources, Bayesian model assessment and selection, approximate inference and information visualization. Our primary application areas are digital health and biology, neuroscience and user interaction.

I'm visiting professor at Technical University of Denmark (DTU), and I have a shared office at Columbia University in the City of New York. I'm member of development teams of Stan, ELFI, GPy and GPstuff.

Areas of expertise

Bayesian modeling Statistical analysis Epidemiology Brain signal analysis Machine learning

Honors and awards

Award or honor granted for a specific work
Department of Computer Science
Jun 2016

2016 De Groot Prize The DeGroot Prize, in honor of Morris H ("Morrie" DeGroot, is awarded to the author or authors of an outstanding published book in Statistical Science

Invitation or ranking in competition
Department of Computer Science
Jan 2004

Member of the winning team (Särkkä, Vehtari & Lampinen) in Time Series Prediction Competition - The CATS Benchmark 2004

Research groups

Professorship Vehtari A., Professor (Associate Professor)
Helsinki Institute for Information Technology HIIT, Professor (Associate Professor)
Probabilistic Machine Learning, Professor (Associate Professor)

Publications

Probabilistic Machine Learning, Professorship Vehtari A., Department of Computer Science, Helsinki Institute for Information Technology HIIT, Multiscale Statistical and Quantum Physics, Department of Applied Physics

Minimum mode saddle point searches using Gaussian process regression with inverse-distance covariance function

Publishing year: 2020 Journal of Chemical Theory and Computation
Centre of Excellence in Computational Inference, COIN, Professorship Kaski S., Helsinki Institute for Information Technology HIIT, Probabilistic Machine Learning, School services, SCI, Department of Computer Science, Professorship Vehtari A., Finnish Center for Artificial Intelligence

Making Bayesian Predictive Models Interpretable: A Decision Theoretic Approach

Publishing year: 2019 Submitted
Professorship Vehtari A., Department of Computer Science, Probabilistic Machine Learning, Helsinki Institute for Information Technology HIIT

Approximate leave-future-out cross-validation for Bayesian time series models

Publishing year: 2019 Computational Statistics
Professorship Vehtari A., Department of Computer Science, Probabilistic Machine Learning, Helsinki Institute for Information Technology HIIT

Leave-one-out cross-validation for non-factorizable normal models

Publishing year: 2019 JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
Department of Computer Science, Centre of Excellence in Molecular Systems Immunology and Physiology Research Group, SyMMys, Professorship Lähdesmäki H., Centre of Excellence in Computational Inference, COIN, Probabilistic Machine Learning, Helsinki Institute for Information Technology HIIT, Professorship Vehtari A.

An additive Gaussian process regression model for interpretable non-parametric analysis of longitudinal data

Publishing year: 2019 Nature Communications
Probabilistic Machine Learning, Helsinki Institute for Information Technology HIIT, Professorship Vehtari A., Department of Computer Science

Visualization in Bayesian workflow

Publishing year: 2019 Journal of the Royal Statistical Society. Series A: Statistics in Society
Department of Computer Science, Professorship Vehtari A., Helsinki Institute for Information Technology HIIT, Probabilistic Machine Learning

R-squared for Bayesian regression models

Publishing year: 2019 AMERICAN STATISTICIAN
Department of Applied Physics, Computational Electronic Structure Theory, Probabilistic Machine Learning, Professorship Vehtari A., Department of Computer Science, Helsinki Institute for Information Technology HIIT

Deep Learning Spectroscopy

Publishing year: 2019 Advanced Science
Centre of Excellence in Computational Inference, COIN, Professorship Kaski S., Helsinki Institute for Information Technology HIIT, Probabilistic Machine Learning, School services, SCI, Department of Computer Science, Professorship Vehtari A., Professorship Marttinen P.

Batch simulations and uncertainty quantification in Gaussian process surrogate-based approximate Bayesian computation

Publishing year: 2019 Submitted
Probabilistic Machine Learning, Helsinki Institute for Information Technology HIIT, Professorship Kaski S., Centre of Excellence in Computational Inference, COIN, Department of Computer Science, Professorship Vehtari A., Professorship Marttinen P.

Efficient acquisition rules for model-based approximate Bayesian computation

Publishing year: 2019 Bayesian Analysis