Explores phase transitions in physics and computational problems, highlighting challenges faced by algorithms and the application of physics principles in understanding neural networks.
Discusses metastability, phase transitions, approximate message passing algorithm limitations, and the efficiency of Langevin dynamics in high-dimensional inference.
Delves into light-induced phase transitions in quantum materials, comparing them to equilibrium transitions and exploring the potential for realizing novel phases.
Explores optimal errors in high-dimensional models, comparing algorithms and shedding light on the interplay between model architecture and performance.