Using Bifurcations for Diversity in Differentiable Games

International Conference on Machine Learning (ICML)


Ridge Rider (RR) is an algorithm for finding diverse solutions to optimization problems by following eigenvectors of the Hessian (“ridges”). RR is designed for conservative gradient systems (i.e. settings involving a single loss function), where it branches at saddles – the only relevant bifurcation points. We generalize this idea to non-conservative, multi-agent gradient systems by identifying new types of bifurcation points and proposing a method to follow eigenvectors with complex eigenvalues. We give theoretical motivation for our method – denoted Game Ridge Rider (GRR) – by leveraging machinery from the field of dynamical systems. Finally, we empirically motivate our method by constructing novel toy problems where we can visualize new phenomena and by finding diverse solutions in the iterated prisoners’ dilemma, where existing methods often converge to a single solution mode.

Related Publications

All Publications

ICML - July 24, 2021

Ditto: Fair and Robust Federated Learning Through Personalization

Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith

ICCV - October 11, 2021

Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing

Garvita Tiwari, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll

Interspeech - September 3, 2021

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

Adam Polyak, Yossi Adi, Jade Copet, Eugene Kharitonov, Kushal Lakhotia, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux

CoNLL - November 9, 2021

Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network

Verna Dankers, Anna Langedijk, Kate McCurdy, Adina Williams, Dieuwke Hupkes

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy