Arno Solin

Arno Solin

Assistant Professor
T313 Dept. Computer Science

I have a broad interest in statistical modelling, machine learning, and signal processing. My key research interests are in Bayesian inference methods for stochastic dynamical systems, linear and non-linear Kalman filtering, and Gaussian process models and infinite-dimensional Kalman filtering for spatio-temporal models.

My application areas revolve around real-time inference applications on limited hardware such as smartphones. These include sensor fusion applications for tracking and localisation, and temporal and spatio-temporal modelling of, e.g., the weather and human brain.

Full researcher profile
https://research.aalto.fi/...

Contact information

Honors and awards

Best Paper Award

Best Paper Award at the Young Demographers conference for the paper "Computationally Inferred Genealogical Networks UncoverLong-Term Trends in Assortative Mating" by Eric Malmi, Aristides Gionis, and Arno Solin.
Award or honor granted for a specific work Department of Computer Science Feb 2018

Best Paper Award at FUSION 2018

The paper "Scalable Magnetic Field SLAM in 3D Using Gaussian Process Maps" by Manon Kok and Arno Solin was awarded the Best Paper award at the FUSION conference in Cambridge, UK.
Award or honor granted for a specific work Professorship Solin Arno Jul 2018

NeurIPS Reviewer Award

Ranked among the top reviewers for NeurIPS 2019.
Award or honor granted for a specific work Department of Computer Science Jan 2019

ICML Reviewer Award

ICML 2020 top reviewer recognition.
Award or honor granted for a specific work Department of Computer Science Jan 2020

NeurIPS Reviewer Award

Ranked among the top reviewers for NeurIPS 2020.
Award or honor granted for a specific work Department of Computer Science Jan 2020

Phase I Finalist in OpenCV AI Competition 2021

An international AI competition celebrating OpenCV's 20th anniversary.
Invitation or ranking in competition Department of Computer Science Jan 2021

Research groups

  • Computer Science Professors, Academy Research Fellow
  • Computer Science - Artificial Intelligence and Machine Learning (AIML), Academy Research Fellow
  • Professorship Solin Arno, Academy Research Fellow

Publications

Non-separable spatio-temporal graph kernels via SPDEs

Alexander Nikitin, Ti John, Arno Solin, Samuel Kaski 2022 Proceedings of The 25th International Conference on Artificial Intelligence and Statistics

Interpolation consistency training for semi-supervised learning

Vikas Verma, Kenji Kawaguchi, Alex Lamb, Juho Kannala, Arno Solin, Yoshua Bengio, David Lopez-Paz 2022 Neural Networks

HybVIO: Pushing the limits of real-time visual-inertial odometry

Otto Seiskari, Pekka Rantalankila, Juho Kannala, Jerry Ylilammi, Esa Rahtu, Arno Solin 2022 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision

Dual parameterization of sparse variational Gaussian processes

Vincent Adam, Paul Chang, Mohammad Emtiyaz Khan, Arno Solin 2021 Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Spatio-temporal variational Gaussian processes

Oliver Hamelijnck, William Wilkinson, Niki Loppi, Arno Solin, Theodoros Damoulas 2021 Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Gaussian Process Priors for View-Aware Inference

Yuxin Hou, Ari Heljakka, Arno Solin 2021 THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

Novel view synthesis via depth-guided skip connections

Yuxin Hou, Arno Solin, Juho Kannala 2021 Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021

Periodic Activation Functions Induce Stationarity

Lassi Meronen, Martin Trapp, Arno Solin 2021 Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Scalable inference in SDEs by direct matching of the Fokker–Planck–Kolmogorov equation

Arno Solin, Ella Tamir, Prakhar Verma 2021 Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Combining pseudo-point and state space approximations for sum-separable Gaussian processes

Will Tebbutt, Arno Solin, Richard E. Turner 2021 Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence