116 citations · 215 across the 8 of their papers we have counts for
4 papers · 1 filter
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single
Paul Vicol, Zico Kolter, Kevin Swersky
We propose an evolution strategies-based algorithm for estimating gradients in unrolled computation graphs, called ES-Single. Similarly to the recently-proposed Persistent Evolutio…
Pre-training helps Bayesian optimization too
Zi Wang, George E. Dahl, Kevin Swersky +6
Bayesian optimization (BO) has become a popular strategy for global optimization of many expensive real-world functions. Contrary to a common belief that BO is suited to optimizing…
Learning unbiased features
Yujia Li, Kevin Swersky, Richard Zemel
A key element in transfer learning is representation learning; if representations can be developed that expose the relevant factors underlying the data, then new tasks and domains…
Estimating the Hessian by Back-propagating Curvature
James Martens, Ilya Sutskever, Kevin Swersky
In this work we develop Curvature Propagation (CP), a general technique for efficiently computing unbiased approximations of the Hessian of any function that is computed using a co…