Alexander Terenin
Alexander Terenin

Alexander Terenin

Assistant Research Professor Cornell University

Research Talks Blog

Research

I study machine learning and artificial intelligence using applied probability. 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 efficiently process information, and then use it to decide what to do: therefore, so should our algorithms.

Talks

An Adversarial Analysis of Thompson Sampling for Full-information Online Learning: from Finite to Infinite Action Spaces

An Adversarial Analysis of Thompson Sampling for Full-information Online Learning: from Finite to Infinite Action Spaces

· INFORMS Applied Probability Society Meeting 2025

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

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

· Carnegie Mellon University

SlidesPrintPDF
Geometric Probabilistic Models

Geometric Probabilistic Models

· Conference on Uncertainty in Artificial Intelligence

SlidesPrintPDFVideo
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

· ETH Zürich

SlidesPrintPDF
Machines Regret Their Actions Too: A Brief Tutorial on Multi-armed Bandits

Machines Regret Their Actions Too: A Brief Tutorial on Multi-armed Bandits

· University of Cambridge

SlidesPrintPDF
All talks

Research Areas and Selected Papers by Topic

The Gittins Index: A Design Principle for Decision-Making Under Uncertainty

The Gittins Index: A Design Principle for Decision-Making Under Uncertainty

Ziv Scully and Alexander Terenin

INFORMS Tutorials in OR 2025

PaperPDF
Bayesian Algorithms for Adversarial Online Learning: from Finite to Infinite Action Spaces

Bayesian Algorithms for Adversarial Online Learning: from Finite to Infinite Action Spaces

Alexander Terenin and Jeffrey Negrea

Preprint

PaperPDF
Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Sidhanth Holalkere, David Bindel, Silvia Sellán, and Alexander Terenin

ICML 2025

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

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

Qian Xie, Raul Astudillo, Peter I. Frazier, Ziv Scully, and Alexander Terenin

NeurIPS 2024

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

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

Theodore Brown, Stephen Marsden, Vignesh Gopakumar, Alexander Terenin, Hong Ge, and Francis Casson

IEEE Transactions on Plasma Science 2024

PaperPDF
Gaussian Processes and Statistical Decision-making in Non-Euclidean Spaces

Gaussian Processes and Statistical Decision-making in Non-Euclidean Spaces

Alexander Terenin

PhD Thesis

PagePDF
The Gittins Index: A Design Principle for Decision-Making Under Uncertainty

The Gittins Index: A Design Principle for Decision-Making Under Uncertainty

Ziv Scully and Alexander Terenin

INFORMS Tutorials in OR 2025

PaperPDF
Bayesian Algorithms for Adversarial Online Learning: from Finite to Infinite Action Spaces

Bayesian Algorithms for Adversarial Online Learning: from Finite to Infinite Action Spaces

Alexander Terenin and Jeffrey Negrea

Preprint

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

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

Qian Xie, Raul Astudillo, Peter I. Frazier, Ziv Scully, and Alexander Terenin

NeurIPS 2024

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

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

Qian Xie, Raul Astudillo, Peter I. Frazier, Ziv Scully, and Alexander Terenin

NeurIPS 2024

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

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

Theodore Brown, Stephen Marsden, Vignesh Gopakumar, Alexander Terenin, Hong Ge, and Francis Casson

IEEE Transactions on Plasma Science 2024

PaperPDF
Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

Noémie Jaquier, Viacheslav Borovitskiy, Andrei Smolensky, Alexander Terenin, Tamim Asfour, and Leonel Rozo

CoRL 2021

PaperPDFCode
Pathwise Conditioning of Gaussian Processes

Pathwise Conditioning of Gaussian Processes

James T. Wilson, Viacheslav Borovitskiy, Alexander Terenin, Peter Mostowsky, and Marc Peter Deisenroth

JMLR 2021

PagePaperPDFCode
Efficiently Sampling Functions from Gaussian Process Posteriors

Efficiently Sampling Functions from Gaussian Process Posteriors

James T. Wilson, Viacheslav Borovitskiy, Alexander Terenin, Peter Mostowsky, and Marc Peter Deisenroth

ICML 2020

PagePaperPDFCodeVideo
Stochastic Gradient Descent for Gaussian Processes Done Right

Stochastic Gradient Descent for Gaussian Processes Done Right

Jihao Andreas Lin, Shreyas Padhy, Javier Antorán, Alexander Terenin, José Miguel Hernández-Lobato, and David Janz

ICLR 2024

PaperPDF
Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees

Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees

Alexander Terenin, David R. Burt, Artem Artemev, Seth Flaxman, Mark van der Wilk, Carl Edward Rasmussen, and Hong Ge

JMLR 2024

PaperPDFCode
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

Jihao Andreas Lin, Javier Antorán, Shreyas Padhy, David Janz, José Miguel Hernández-Lobato, and Alexander Terenin

NeurIPS 2023

PagePaperPDFCode
Pathwise Conditioning of Gaussian Processes

Pathwise Conditioning of Gaussian Processes

James T. Wilson, Viacheslav Borovitskiy, Alexander Terenin, Peter Mostowsky, and Marc Peter Deisenroth

JMLR 2021

PagePaperPDFCode
Efficiently Sampling Functions from Gaussian Process Posteriors

Efficiently Sampling Functions from Gaussian Process Posteriors

James T. Wilson, Viacheslav Borovitskiy, Alexander Terenin, Peter Mostowsky, and Marc Peter Deisenroth

ICML 2020

PagePaperPDFCodeVideo
Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Sidhanth Holalkere, David Bindel, Silvia Sellán, and Alexander Terenin

ICML 2025

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

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

Peter Mostowsky, Vincent Dutordoir, Iskander Azangulov, Noémie Jaquier, Michael John Hutchinson, Aditya Ravuri, Leonel Rozo, Alexander Terenin, and Viacheslav Borovitskiy

Preprint

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

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

Iskander Azangulov, Andrei Smolensky, Alexander Terenin, and Viacheslav Borovitskiy

JMLR 2024

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

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

Iskander Azangulov, Andrei Smolensky, Alexander Terenin, and Viacheslav Borovitskiy

JMLR 2024

PaperPDFCode
Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds

Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds

Paul Rosa, Viacheslav Borovitskiy, Alexander Terenin, and Judith Rousseau

NeurIPS 2023

PaperPDFCode
Gaussian Processes and Statistical Decision-making in Non-Euclidean Spaces

Gaussian Processes and Statistical Decision-making in Non-Euclidean Spaces

Alexander Terenin

PhD Thesis

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

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

Michael John Hutchinson, Alexander Terenin, Viacheslav Borovitskiy, So Takao, Yee Whye Teh, and Marc Peter Deisenroth

NeurIPS 2021

PagePaperPDFCodeVideo
Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

Noémie Jaquier, Viacheslav Borovitskiy, Andrei Smolensky, Alexander Terenin, Tamim Asfour, and Leonel Rozo

CoRL 2021

PaperPDFCode
Matérn Gaussian Processes on Graphs

Matérn Gaussian Processes on Graphs

Viacheslav Borovitskiy, Iskander Azangulov, Alexander Terenin, Peter Mostowsky, Marc Peter Deisenroth, and Nicolas Durrande

AISTATS 2021

PagePaperPDFCodeVideo
Matérn Gaussian Processes on Riemannian Manifolds

Matérn Gaussian Processes on Riemannian Manifolds

Viacheslav Borovitskiy, Alexander Terenin, Peter Mostowsky, and Marc Peter Deisenroth

NeurIPS 2020

PagePaperPDFCode
Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Sidhanth Holalkere, David Bindel, Silvia Sellán, and Alexander Terenin

ICML 2025

PagePaperPDF
A Unifying Variational Framework for Gaussian Process Motion Planning

A Unifying Variational Framework for Gaussian Process Motion Planning

Lucas Cosier, Rares Iordan, Sicelukwanda N. T. Zwane, Giovanni Franzese, James T. Wilson, Marc Peter Deisenroth, Alexander Terenin, and Yasemin Bekiroğlu

AISTATS 2024

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

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

Theodore Brown, Stephen Marsden, Vignesh Gopakumar, Alexander Terenin, Hong Ge, and Francis Casson

IEEE Transactions on Plasma Science 2024

PaperPDF
The Cambridge Law Corpus: A Dataset for Legal AI Research

The Cambridge Law Corpus: A Dataset for Legal AI Research

Andreas Östling, Holli Sargeant, Huiyuan Xie, Ludwig Bull, Alexander Terenin, Leif Jonsson, Måns Magnusson, and Felix Steffek

NeurIPS 2023

PagePaperPDF
Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels

Noémie Jaquier, Viacheslav Borovitskiy, Andrei Smolensky, Alexander Terenin, Tamim Asfour, and Leonel Rozo

CoRL 2021

PaperPDFCode
Learning Contact Dynamics using Physically Structured Neural Networks

Learning Contact Dynamics using Physically Structured Neural Networks

Andreas Hochlehnert, Alexander Terenin, Steindór Sæmundsson, and Marc Peter Deisenroth

AISTATS 2021

PagePaperPDFCodeVideo
Aligning Time Series on Incomparable Spaces

Aligning Time Series on Incomparable Spaces

Samuel Cohen, Giulia Luise, Alexander Terenin, Brandon Amos, and Marc Peter Deisenroth

AISTATS 2021

PagePaperPDFCodeVideo
Variational Integrator Networks for Physically Structured Embeddings

Variational Integrator Networks for Physically Structured Embeddings

Steindór Sæmundsson, Alexander Terenin, Katja Hofmann, and Marc Peter Deisenroth

AISTATS 2020

PagePaperPDFCode
Sparse Parallel Training of Hierarchical Dirichlet Process Topic Models

Sparse Parallel Training of Hierarchical Dirichlet Process Topic Models

Alexander Terenin, Måns Magnusson, and Leif Jonsson

EMNLP 2020

PaperPDFCode
Pólya Urn Latent Dirichlet Allocation: A Doubly Sparse Massively Parallel Sampler

Pólya Urn Latent Dirichlet Allocation: A Doubly Sparse Massively Parallel Sampler

Alexander Terenin, Måns Magnusson, Leif Jonsson, and David Draper

IEEE TPAMI 2019

PaperPDFCode
Additional papers

Blog

On Successful Research

On Successful Research

All posts
Morty Proxy This is a proxified and sanitized view of the page, visit original site.