You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Updated paper on implicit competitive regularization in #GANs https://arxiv.org/abs/1910.05852 Blog: https://f-t-s.github.io/projects/icr/ GANs work due to simultaneous optimization of generator & discriminator; not choice of divergence. With Florian Schaefer @Kay12400259 @Caltechpic.twitter.com/QwmJgJhzDZ
GANs work when both agents are simultaneously updated. If one agent is fixed and other updated, performance worsens. Hence, GANs don't converge to Nash. Instead, implicit regularization from simultaneous updates is key to good performance.pic.twitter.com/jIEwOpGGwg
Implicit competitive regularization in GANs encourages discriminators to learn slowly. It is more effective than explicit gradient penalties. Competitive gradient descent further strengthens this implicit reg. by using mixed Hessian to account for interaction among playerspic.twitter.com/t5yXDYYhMK
For details on competitive gradient descent, check out this threadhttps://twitter.com/AnimaAnandkumar/status/1205173860284293121?s=20 …
GANs are framed as a competition between generator and discriminator. Our work shows, in addition, cooperation is essential to stabilize training and avoid oscillations/mode collapse. Cooperation arises from simultaneous optimization. Our method CGD further enhances this.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
