Log In Sign Up

EigenGame Unloaded: When playing games is better than optimizing

by   Ian Gemp, et al.

We build on the recently proposed EigenGame that views eigendecomposition as a competitive game. EigenGame's updates are biased if computed using minibatches of data, which hinders convergence and more sophisticated parallelism in the stochastic setting. In this work, we propose an unbiased stochastic update that is asymptotically equivalent to EigenGame, enjoys greater parallelism allowing computation on datasets of larger sample sizes, and outperforms EigenGame in experiments. We present applications to finding the principal components of massive datasets and performing spectral clustering of graphs. We analyze and discuss our proposed update in the context of EigenGame and the shift in perspective from optimization to games.


page 13

page 14


Role of normalization in spectral clustering for stochastic blockmodels

Spectral clustering is a technique that clusters elements using the top ...

Algebra of Concurrent Games

We introduce parallelism into the basic algebra of games to model concur...

Fictitious play in zero-sum stochastic games

We present fictitious play dynamics for the general class of stochastic ...

Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures

Recently, Optimistic Multiplicative Weights Update (OMWU) was proven to ...

Clustering dynamics on graphs: from spectral clustering to mean shift through Fokker-Planck interpolation

In this work we build a unifying framework to interpolate between densit...