Abstract: The framework of integral quadratic constraints is used to perform an analysis of gradient descent with varying step sizes. Two performance metrics are considered: convergence rate and noise ...
Abstract: Stein variational gradient descent (SVGD) is a prominent particle-based variational inference method used for sampling a target distribution. In this paper, we propose two novel trainable ...
This is a new engine for Descent 3, from the initial 1.5 source code release. It incorporates almost every change from InjectD3, among many more. At the moment, this includes the following features: ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback