Devon Graham — accepted AI-conference papers

2020

ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool

Gellert Weisz, András György, Wei-I Lin, Devon Graham, Kevin Leyton-Brown, Csaba Szepesvari +1

NeurIPS 2020poster

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 successfu…

Cited by 6 Source ↗PDF ↗Scholar ↗

2019

Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration

Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier, Devon Graham

NeurIPS 2019poster

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 (

Cited by 31 Source ↗PDF ↗code ↗Scholar ↗

2018

Deep Models of Interactions Across Sets

Jason Hartford, Devon Graham, Kevin Leyton-Brown, Siamak Ravanbakhsh

ICML 2018oral

We use deep learning to model interactions across two or more sets of objects, such as user{–}movie ratings or protein{–}drug bindings. The canonical representation of such interactions is a matrix (or tensor) with an exchangeability property: the encoding’s meaning is not changed by permuting rows…

Cited by 189 Source ↗PDF ↗code ↗Scholar ↗