Timezone: »

Geometrically Coupled Monte Carlo Sampling
Mark Rowland · Krzysztof Choromanski · François Chalus · Aldo Pacchiano · Tamas Sarlos · Richard Turner · Adrian Weller

Wed Dec 05 01:50 PM -- 01:55 PM (PST) @ Room 220 CD

Monte Carlo sampling in high-dimensional, low-sample settings is important in many machine learning tasks. We improve current methods for sampling in Euclidean spaces by avoiding independence, and instead consider ways to couple samples. We show fundamental connections to optimal transport theory, leading to novel sampling algorithms, and providing new theoretical grounding for existing strategies. We compare our new strategies against prior methods for improving sample efficiency, including QMC, by studying discrepancy. We explore our findings empirically, and observe benefits of our sampling schemes for reinforcement learning and generative modelling.

Author Information

Mark Rowland (University of Cambridge)
Krzysztof Choromanski (Google Brain Robotics)
François Chalus (Credit Suisse & University of Cambridge)
Aldo Pacchiano (UC Berkeley)
Tamas Sarlos (Google Research)
Richard Turner (University of Cambridge)
Adrian Weller (University of Cambridge)

Adrian Weller is Programme Director for AI at The Alan Turing Institute, the UK national institute for data science and AI, where he is also a Turing Fellow leading work on safe and ethical AI. He is a Senior Research Fellow in Machine Learning at the University of Cambridge, and at the Leverhulme Centre for the Future of Intelligence where he leads the project on Trust and Transparency. His interests span AI, its commercial applications and helping to ensure beneficial outcomes for society. He serves on several boards including the Centre for Data Ethics and Innovation. Previously, Adrian held senior roles in finance.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors