What I Read: Game theory for large-scale data analysis

https://deepmind.com/blog/article/EigenGame

06 May 2021
Game theory as an engine for large-scale data analysis
Brian McWilliams
Ian Gemp
Claire Vernade


“…we reformulated principal component analysis (PCA)… as a competitive multi-agent game we call EigenGame. PCA is typically formulated as an optimisation problem (or single-agent problem); however, we found that the multi-agent perspective allowed us to… scale to massive data sets that previously would have been too computationally demanding, and offers an alternative approach for future exploration.”