Black-Box Optimization with a Politician

Abstract

We propose a new framework for black-box convex optimization which is well-suited for situations where gradient computations are expensive. We derive a new method for this framework which leverages several concepts from convex optimization, from standard first-order methods (e.g. gradient descent or quasi-Newton methods) to analytical centers (i.e. minimizers of self-concordant barriers). We demonstrate empirically that our new technique compares favorably with state of the art algorithms (such as BFGS).

Cite

Text

Bubeck and Lee. "Black-Box Optimization with a Politician." International Conference on Machine Learning, 2016.

Markdown

[Bubeck and Lee. "Black-Box Optimization with a Politician." International Conference on Machine Learning, 2016.](https://mlanthology.org/icml/2016/bubeck2016icml-blackbox/)

BibTeX

@inproceedings{bubeck2016icml-blackbox,
  title     = {{Black-Box Optimization with a Politician}},
  author    = {Bubeck, Sebastien and Lee, Yin Tat},
  booktitle = {International Conference on Machine Learning},
  year      = {2016},
  pages     = {1624-1631},
  volume    = {48},
  url       = {https://mlanthology.org/icml/2016/bubeck2016icml-blackbox/}
}