Timezone: »

ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool
Gellert Weisz · András György · Wei-I Lin · Devon Graham · Kevin Leyton-Brown · Csaba Szepesvari · Brendan Lucier

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #1787

Algorithm configuration procedures optimize parameters of a given algorithm to perform well over a distribution of inputs. Recent theoretical work focused on the case of selecting between a small number of alternatives. In practice, parameter spaces are often very large or infinite, and so successful heuristic procedures discard parameters ``impatiently'', based on very few observations. Inspired by this idea, we introduce ImpatientCapsAndRuns, which quickly discards less promising configurations, significantly speeding up the search procedure compared to previous algorithms with theoretical guarantees, while still achieving optimal runtime up to logarithmic factors under mild assumptions. Experimental results demonstrate a practical improvement.

Author Information

Gellert Weisz (Deepmind)
András György (DeepMind)
Wei-I Lin (UBC)
Devon Graham (University of British Columbia)
Kevin Leyton-Brown (University of British Columbia)
Csaba Szepesvari (DeepMind / University of Alberta)
Brendan Lucier (Microsoft Research)

More from the Same Authors