Log In Sign Up

EigenGame: PCA as a Nash Equilibrium

by   Ian Gemp, et al.

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.


page 9

page 16


Principal Component Analysis Based on Tℓ_1-norm Maximization

Classical principal component analysis (PCA) may suffer from the sensiti...

Self-adaptive node-based PCA encodings

In this paper we propose an algorithm, Simple Hebbian PCA, and prove tha...

All Sparse PCA Models Are Wrong, But Some Are Useful. Part I: Computation of Scores, Residuals and Explained Variance

Sparse Principal Component Analysis (sPCA) is a popular matrix factoriza...

Learning a Factor Model via Regularized PCA

We consider the problem of learning a linear factor model. We propose a ...

Utility of PCA and Other Data Transformation Techniques in Exoplanet Research

This paper focuses on the utility of various data transformation techniq...

Principal Trade-off Analysis

This paper develops Principal Trade-off Analysis (PTA), a decomposition ...

Deep Contrastive Learning is Provably (almost) Principal Component Analysis

We show that Contrastive Learning (CL) under a family of loss functions ...

Code Repositories