Alexander Terenin

Research

I study machine learning and artificial intelligence. Developing a principled understanding of decision-making and explore-exploit tradeoffs is the next key step on the path to creating machine intelligence. The brain evolved to process information efficiently: therefore, so should our algorithms.

Talks

Geometric Probabilistic Models

· Conference on Uncertainty in Artificial Intelligence

Research Areas and Selected Papers by Topic

Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index

NeurIPS 2024

The GeometricKernels Package: Heat and Matérn Kernels for Geometric Learning on Manifolds, Meshes, and Graphs

Preprint

Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces

JMLR 2024

Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case

JMLR 2024

Stochastic Gradient Descent for Gaussian Processes Done Right

ICLR 2024

A Unifying Variational Framework for Gaussian Process Motion Planning

AISTATS 2024

Multi-objective Bayesian optimisation for design of Pareto-optimal current drive profiles in STEP

IEEE Transactions on Plasma Science 2024

Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees

JMLR 2024

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

NeurIPS 2023

Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds

NeurIPS 2023

The Cambridge Law Corpus: A Dataset for Legal AI Research

NeurIPS 2023

Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index

NeurIPS 2024

Multi-objective Bayesian optimisation for design of Pareto-optimal current drive profiles in STEP

IEEE Transactions on Plasma Science 2024

Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

CoRL 2021

Pathwise Conditioning of Gaussian Processes

JMLR 2021

Efficiently Sampling Functions from Gaussian Process Posteriors

ICML 2020

Stochastic Gradient Descent for Gaussian Processes Done Right

ICLR 2024

Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees

JMLR 2024

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

NeurIPS 2023

Pathwise Conditioning of Gaussian Processes

JMLR 2021

Efficiently Sampling Functions from Gaussian Process Posteriors

ICML 2020

The GeometricKernels Package: Heat and Matérn Kernels for Geometric Learning on Manifolds, Meshes, and Graphs

Preprint

Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces

JMLR 2024

Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case

JMLR 2024

Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds

NeurIPS 2023

Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels

NeurIPS 2021

Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

CoRL 2021

Matérn Gaussian Processes on Graphs

AISTATS 2021

Matérn Gaussian Processes on Riemannian Manifolds

NeurIPS 2020

Learning Contact Dynamics using Physically Structured Neural Networks

AISTATS 2021

Variational Integrator Networks for Physically Structured Embeddings

AISTATS 2020

A Unifying Variational Framework for Gaussian Process Motion Planning

AISTATS 2024

Multi-objective Bayesian optimisation for design of Pareto-optimal current drive profiles in STEP

IEEE Transactions on Plasma Science 2024

The Cambridge Law Corpus: A Dataset for Legal AI Research

NeurIPS 2023

Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

CoRL 2021

Aligning Time Series on Incomparable Spaces

AISTATS 2021