Game theory as an engine for large-scale data analysis | DeepMind
Our research explored a new approach to an old problem: we reformulated principal component analysis (PCA), a type of eigenvalue problem, as a competitive multi-agent game we call EigenGame.
Game theory as an engine for large-scale data analysis — Google DeepMind Skip to main content May 6, 2021 Research Game theory as an engine for large-scale data analysis Brian McWilliams, Ian Gemp, Claire Vernade Share EigenGame maps out a new approach to solve fundamental ML problems Modern AI systems approach tasks like recognising objects in images and predicting the 3D structure of proteins as a diligent student would prepare for an exam. By training on many example problems, they minimise their mistakes over time until they achieve success. But this is a solitary endeavour and only one of
saved by
related reading
- Game theory as an engine for large-scale data analysis — Google DeepMinddeepmind.google
- Consensus Multiplicative Weights Update: Learningto Learn using Projector-based Game Signaturesarxiv.org
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- Towards a scale-free theory of intelligent agencymindthefuture.info
- AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms — Google DeepMinddeepmind.google
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- How DeepMind's Generally Capable Agents Were Trained — LessWronglesswrong.com
- VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pokémonarxiv.org
- A Pragmatic Vision for Interpretability — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
- Shapley value: from cooperative game to explainable artificial intelligence | Autonomous Intelligent Systems | Springer Nature Linklink.springer.com