Joint research led by Sosuke Ito of the University of Tokyo has shown that nonequilibrium thermodynamics, a branch of physics that deals with constantly changing systems, explains why optimal transport theory, a mathematical framework for the optimal change of distribution to reduce cost, makes generative models optimal. As nonequilibrium thermodynamics has yet to be fully leveraged in designing generative models, the discovery offers a novel thermodynamic approach to machine learning research. The findings were published in the journal Physical Review X.
A thermodynamic approach to machine learning: How optimal transport theory can improve generative models
Reader’s Picks
-
New research published in the journal Frontiers in Psychology reveals how extremist groups are exploiting the popularity of video games [...]
-
If scientists are to better understand whether the genes that let us welcome the weekend with a cold beer or [...]
-
When it comes to susceptibility to influence on social media, “It’s not just about who you are—it’s about where you [...]