Sho Yaida

Sho is a research scientist at Facebook AI Research (FAIR), focusing on the physics of machine learning. He studied black holes while earning his Ph.D. at Stanford University, before shifting to cracking the glass problem during postdoc work at MIT and Duke University.

Sho's Publications

May 08, 2019



Fluctuation-dissipation relations for stochastic gradient descent

The notion of the stationary equilibrium ensemble has played a central role in statistical mechanics. In machine learning as well, training serves as generalized equilibration that drives the probability distribution of model parameters toward…

Sho Yaida,

May 08, 2019