Motonobu Kanagawa

Assistant Professor

Email LinkedIn Google Scholar BleuSky

I am an Assistant Professor (Maitre de Conférences) in the Data Science Department at EURECOM in France since 2019. Previously, I was a research scientist at the University of Tuebingen and the Max Planck Institute for Intelligent Systems in Germany with Prof. Philipp Hennig (2017-2019). I obtained a PhD in 2016 at the Institute of Statistical Mathematics in Tokyo with Prof. Kenji Fukumizu.
Research interests: Statistics, Machine Learning and Simulation
Simulations enable understanding complex systems or phenomena appearing in many areas of science and engineering, such as climate, disasters, economics and finance. A simulator’s reliability, however, depends on various factors, such as the accuracy in approximating the system under analysis and the accuracy in numerical computation. One of my recent interests is statistical learning methods for automatically verifying those factors.

Motonobu’s Publications

Variable Selection for Comparing High-dimensional Time-Series Data

Variable Selection for Comparing High-dimensional Time-Series Data
Kensuke Mitsuzawa, Margherita Grossi, Stefano Bortoli, Motonobu Kanagawa
CoRR (2024)

preprint URL

Fast Computation of Leave-One-Out Cross-Validation for k-NN Regression

Fast Computation of Leave-One-Out Cross-Validation for k-NN Regression
Motonobu Kanagawa
CoRR (2024)

preprint URL

Improved Random Features for Dot Product Kernels
Jonas Wacker, Motonobu Kanagawa, Maurizio Filippone
J. Mach. Learn. Res. (2024)

journal URL

Variable Selection in Maximum Mean Discrepancy for Interpretable Distribution Comparison

Variable Selection in Maximum Mean Discrepancy for Interpretable Distribution Comparison
Kensuke Mitsuzawa, Motonobu Kanagawa, Stefano Bortoli, Margherita Grossi, Paolo Papotti
CoRR (2023)

preprint URL

When is Importance Weighting Correction Needed for Covariate Shift Adaptation?

When is Importance Weighting Correction Needed for Covariate Shift Adaptation?
Davit Gogolashvili, Matteo Zecchin, Motonobu Kanagawa, Marios Kountouris, Maurizio Filippone
CoRR (2023)

preprint URL

Connections and Equivalences between the Nyström Method and Sparse Variational Gaussian Processes

Connections and Equivalences between the Nyström Method and Sparse Variational Gaussian Processes
Veit Wild, Motonobu Kanagawa, Dino Sejdinovic
CoRR (2021)

preprint URL

Counterfactual Mean Embeddings
Krikamol Muandet, Motonobu Kanagawa, Sorawit Saengkyongam, Sanparith Marukatat
J. Mach. Learn. Res. (2021)

journal URL

Simulator Calibration under Covariate Shift with Kernels
Keiichi Kisamori, Motonobu Kanagawa, Keisuke Yamazaki
The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy] (2020)

journal URL

Model-based kernel sum rule: kernel Bayesian inference with probabilistic models
Yu Nishiyama, Motonobu Kanagawa, Arthur Gretton, Kenji Fukumizu
Mach. Learn. (2020)

journal URL

Convergence Analysis of Deterministic Kernel-Based Quadrature Rules in Misspecified Settings
Motonobu Kanagawa, Bharath K. Sriperumbudur, Kenji Fukumizu
Found. Comput. Math. (2020)

journal URL

Model Selection for Simulator-based Statistical Models: A Kernel Approach

Model Selection for Simulator-based Statistical Models: A Kernel Approach
Takafumi Kajihara, Motonobu Kanagawa, Yuuki Nakaguchi, Kanishka Khandelwal, Kenji Fukumizu
CoRR (2019)

preprint URL

Convergence Guarantees for Adaptive Bayesian Quadrature Methods

Convergence Guarantees for Adaptive Bayesian Quadrature Methods
Motonobu Kanagawa, Philipp Hennig
Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada (2019)

journal URL

On the positivity and magnitudes of Bayesian quadrature weights
Toni Karvonen, Motonobu Kanagawa, Simo Sarkka
Stat. Comput. (2019)

journal URL

Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences

Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic, Bharath K. Sriperumbudur
CoRR (2018)

preprint URL

Counterfactual Mean Embedding: A Kernel Method for Nonparametric Causal Inference

Counterfactual Mean Embedding: A Kernel Method for Nonparametric Causal Inference
Krikamol Muandet, Motonobu Kanagawa, Sorawit Saengkyongam, Sanparith Marukatat
CoRR (2018)

preprint URL

Kernel Recursive ABC: Point Estimation with Intractable Likelihood

Kernel Recursive ABC: Point Estimation with Intractable Likelihood
Takafumi Kajihara, Motonobu Kanagawa, Keisuke Yamazaki, Kenji Fukumizu
Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018 (2018)

journal URL

Unsupervised group matching with application to cross-lingual topic matching without alignment information
Tomoharu Iwata, Motonobu Kanagawa, Tsutomu Hirao, Kenji Fukumizu
Data Min. Knowl. Discov. (2017)

journal URL

Convergence guarantees for kernel-based quadrature rules in misspecified settings
Motonobu Kanagawa, Bharath K. Sriperumbudur, Kenji Fukumizu
Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain (2016)

journal URL

Filtering with State-Observation Examples via Kernel Monte Carlo Filter
Motonobu Kanagawa, Yu Nishiyama, Arthur Gretton, Kenji Fukumizu
Neural Comput. (2016)

journal URL

No matching items