Continuum Limit
The continuum limit explores the behavior of systems as their discrete components become infinitely small, effectively transitioning from a discrete to a continuous representation. Current research focuses on understanding and quantifying the limitations of this transition in various domains, including neural networks, agent-based models, and dynamical systems, often employing techniques like metric entropy analysis and novel algorithms for improved approximation and efficiency. These investigations are crucial for advancing our understanding of complex systems and improving the performance of machine learning models and other computational methods in scenarios with limited resources or inherent constraints.
Papers
On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
Jordi Armengol-Estapé, Vincent Michalski, Ramnath Kumar, Pierre-Luc St-Charles, Doina Precup, Samira Ebrahimi Kahou
Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits
Haya Diwan, Jinrui Gou, Cameron Musco, Christopher Musco, Torsten Suel