Explores phase transitions in physics and computational problems, highlighting challenges faced by algorithms and the application of physics principles in understanding neural networks.
Explores the formulation and complexity of Support Vector Machines, including primal and dual forms, geometric interpretation, and algorithmic implications.
Explores challenges in identifying useful metastable materials and discusses concepts like structure predictions, ensemble probabilities, and mapping algorithms.
Covers transformer architecture and subquadratic attention mechanisms, focusing on efficient approximations and their applications in machine learning.