4 papers
Mirror flows and -Laplacian eigenvalue problems on metric measure spaces
Sho Shimoyama
We study mirror flows as Banach-space counterparts of Hilbertian gradient flows and show that they play an essential role in -Laplacian eigenvalue problems on metric measure spa…
On gradient descent-ascent flows in metric spaces
Noboru Isobe, Sho Shimoyama
Gradient descent-ascent (GDA) flows play a central role in finding saddle points of bivariate functionals, with applications in optimization, game theory, and robust control. While…
Transformation of -gradient flows to -gradient flows in metric spaces
Sho Shimoyama
We explicitly construct parameter transformations between gradient flows in metric spaces, called curves of maximal slope, having different exponents when the associated function s…
Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative
Sho Shimoyama, Tetsuro Morimura, Kenshi Abe +6
Dialog policies, which determine a system's action based on the current state at each dialog turn, are crucial to the success of the dialog. In recent years, reinforcement learning…