Timezone: »

Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration
Robert Kleinberg · Kevin Leyton-Brown · Brendan Lucier · Devon Graham

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #34

Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure (Structured Procrastination'') that provably achieves near optimal performance with high probability and with nearly minimal runtime in the worst case. It also offers an anytime property: it keeps tightening its optimality guarantees the longer it is run. Unfortunately, Structured Procrastination is not adaptive to characteristics of the parameterized algorithm: it treats every input like the worst case. Follow-up work (LeapsAndBounds'') achieves adaptivity but trades away the anytime property. This paper introduces a new algorithm, ``Structured Procrastination with Confidence'', that preserves the near-optimality and anytime properties of Structured Procrastination while adding adaptivity. In particular, the new algorithm will perform dramatically faster in settings where many algorithm configurations perform poorly. We show empirically both that such settings arise frequently in practice and that the anytime property is useful for finding good configurations quickly.

Author Information

Robert Kleinberg (Cornell University)
Kevin Leyton-Brown (University of British Columbia)
Brendan Lucier (Microsoft Research)
Devon Graham (University of British Columbia)

More from the Same Authors