Black-box Optimization with a Politician

Sebastien Bubeck, Yin Tat Lee
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:1624-1631, 2016.

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 this Paper


BibTeX
@InProceedings{pmlr-v48-bubeck16, title = {Black-box Optimization with a Politician}, author = {Bubeck, Sebastien and Lee, Yin Tat}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {1624--1631}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/bubeck16.pdf}, url = {https://proceedings.mlr.press/v48/bubeck16.html}, 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).} }
Endnote
%0 Conference Paper %T Black-box Optimization with a Politician %A Sebastien Bubeck %A Yin Tat Lee %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-bubeck16 %I PMLR %P 1624--1631 %U https://proceedings.mlr.press/v48/bubeck16.html %V 48 %X 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).
RIS
TY - CPAPER TI - Black-box Optimization with a Politician AU - Sebastien Bubeck AU - Yin Tat Lee BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-bubeck16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 1624 EP - 1631 L1 - http://proceedings.mlr.press/v48/bubeck16.pdf UR - https://proceedings.mlr.press/v48/bubeck16.html AB - 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). ER -
APA
Bubeck, S. & Lee, Y.T.. (2016). Black-box Optimization with a Politician. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:1624-1631 Available from https://proceedings.mlr.press/v48/bubeck16.html.

Related Material