Is this related to leapfrog integration as used in HMC?
For saddle point problems and more general games, gradient descent can cycle and diverge. Using an extrapolation steps adresses this issue and converges to a saddle point (Nash equilibrium). https://en.wikipedia.org/wiki/Variational_inequality …pic.twitter.com/Kpxbd2Cqbh
-
-
-
Yes exactly I think these are all symplectic integrators.
Kraj razgovora
Novi razgovor -
-
-
We have a new method called competitve gradient descent that uses mixed hessian. Unlike extra gradients these can work with high learning rateshttps://twitter.com/AnimaAnandkumar/status/1205173860284293121?s=20 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Some GAN papers using this idea: https://arxiv.org/pdf/1807.02629.pdf … https://arxiv.org/pdf/1904.08598.pdf …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
when coordinnates are (x_1,x_2) you shouldn't use x_t , x_{t+1/2} and x_{t+1} for the sequence of points in gradient descent
- Još 1 odgovor
Novi razgovor -
-
Tweet je nedostupan.
-
-
Do you know a good source on what's known about last iterate conference such as this? E.g. do we need to use L2 distance or can we do general Bregman divergences etc.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.