Optimizing Millions of Hyperparameters by Implicit Differentiation

6 Nov 2019Jonathan LorrainePaul VicolDavid Duvenaud

We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT and differentiating through optimization, motivating our algorithm... (read more)

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.