We present a novel view on principal component analysis (PCA) as a competitive game in which each approximate eigenvector is controlled by a player whose goal is to maximize their own utility function. We analyze the properties of this PCA game and the behavior of its gradient based updates. The resulting algorithm — which combines elements from Oja’s rule with a generalized Gram-Schmidt orthogonalization — is naturally decentralized and hence parallelizable through message passing. We demonstrate the scalability of the algorithm with experiments on large image datasets and neural network activations. We discuss how this new view of PCA as a differentiable game can lead to further algorithmic developments and insights.

Game theory as an engine for large-scale data analysis
EigenGame maps out a original plot to resolve traditional ML complications. Up-to-the-minute AI systems plot tasks love recognising objects in

#PCA #ML #AL #Probyto #ProbytoAI

Subscribe and follow us for latest news in Data Science, Machine learning, technology and stay updated!

Facebook: https://facebook.com/probyto
Twitter: https://twitter.com/probyto
LinkedIn: https://linkedin.com/company/probyto
Instagram: https://instagram.com/probyto