About
I'm a researcher working on statistical machine learning and artificial intelligence. My work, which has twice won best-paper-type awards at top machine learning conferences, focuses on how to learn efficiently from data, and how to automatically gather data. The brain evolved to process information efficiently: therefore, so should our algorithms.
Research Expertise and Current Interests
Data-efficient learning. Gaussian processes, physically structured neural networks, symmetries and inductive biases, non-Euclidean learning.
Where to gather data? Bayesian optimization, Bayesian interactive decision-making, planning under uncertainty, reinforcement learning.
Research
Talks
Machines Regret Their Actions Too: A Brief Tutorial on Multi-armed Bandits
· University of Cambridge
Publications
Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels
Michael Hutchinson,* Alexander Terenin*, Viacheslav Borovitskiy,* So Takao,* Yee Whye Teh, and Marc Peter Deisenroth
NeurIPS 2021
Learning Contact Dynamics using Physically Structured Neural Networks
Andreas Hochlehnert, Alexander Terenin, Steindór Sæmundsson, Marc Peter Deisenroth
AISTATS 2021
Pathwise Conditioning of Gaussian Processes
James T. Wilson,* Viacheslav Borovitskiy,* Alexander Terenin,* Peter Mostowsky,* Marc Peter Deisenroth
JMLR 2021
Matérn Gaussian Processes on Graphs
Viacheslav Borovitskiy,* Iskander Azangulov,* Alexander Terenin,* Peter Mostowsky, Marc Peter Deisenroth, Nicolas Durrande
AISTATS 2021
Matérn Gaussian Processes on Riemannian Manifolds
Viacheslav Borovitskiy,* Alexander Terenin,* Peter Mostowsky,* Marc Peter Deisenroth
NeurIPS 2020
Aligning Time Series on Incomparable Spaces
Samuel Cohen, Giulia Luise, Alexander Terenin, Brandon Amos, Marc Peter Deisenroth
AISTATS 2021
Variational Integrator Networks for Physically Structured Embeddings
Steindór Sæmundsson, Alexander Terenin, Katja Hofmann, Marc Peter Deisenroth
AISTATS 2020