Sustainability and Machine Learning Group
Sustainability and Machine Learning Group
Home
Team
Publications
Blog
Teaching
Talks
News
Openings
1
Watch Less and Uncover More: Could Navigation Tools Help Users Search and Explore Videos?
Maria Perez-Ortiz
,
Sahan Bulathwela
,
Claire Dormann
,
Meghana Verma
,
Stefan Kreitmayer
,
Richard Noss
,
John Shawe-Taylor
,
Yvonne Rogers
,
Emine Yilmaz
Cite
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 J. Hutchinson
,
Alexander Terenin
,
Viacheslav Borovitskiy
,
So Takao
,
Yee Whye Teh
,
Marc P. Deisenroth
PDF
Cite
Code
Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels
Noémie Jaquier
,
Viacheslav Borovitskiy
,
Andrei Smolensky
,
Alexander Terenin
,
Tamim Asfour
,
Leonel Rozo
PDF
Cite
Code
Discretization Drift in Two-Player Games
Gradient-based methods for two-player games produce rich dynamics that can solve challenging problems, yet can be difficult to …
Mihaela Rosca
,
Yan Wu
,
Benoit Dherin
,
David Barrett
PDF
Cite
Code
Riemannian Convex Potential Flows
Modeling distributions on Riemannian manifolds is a crucial component in understanding nonEuclidean data that arises, e.g., in physics …
Samuel Cohen
,
Brandon Amos
,
Yaron Lipman
PDF
Cite
Code
Spectral Normalization for Deep Reinforcement Learning: an Optimisation Perspective
Most of the recent deep reinforcement learning advances take an RL-centric perspective and focus on refinements of the training …
Florin Gogianu
,
Tudor Berariu
,
Mihaela Rosca
,
Claudia Clopath
,
Lucian Busoniu
,
Razvan Pascanu
PDF
Cite
Code
Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities
Advances in algorithmic fairness have largely omitted sexual orientation and gender identity. We explore queer concerns in privacy, …
Nenad Tomasev
,
Kevin R. McKee
,
Jackie Kay
,
Shakir Mohamed
PDF
Cite
A Practical Sparse Approximation for Real Time Recurrent Learning
Recurrent neural networks are usually trained with backpropagation through time, which requires storing a complete history of network …
Jacob Menick
,
Erich Elsen
,
Utku Evci
,
Simon Osindero
,
Karen Simonyan
,
Alex Graves
PDF
Cite
Aligning Time Series on Incomparable Spaces
Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in …
Samuel Cohen
,
Giulia Luise
,
Alexander Terenin
,
Brandon Amos
,
Marc Deisenroth
PDF
Cite
Code
Learning Contact Dynamics using Physically Structured Neural Networks
Learning physically structured representations of dynamical systems that include contact between different objects is an important …
Andreas Hochlehnert
,
Alexander Terenin
,
Steindór Sæmundsson
,
Marc Deisenroth
PDF
Cite
Code
«
»
Cite
×