ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool

no code implementations • NeurIPS 2020 • Gellert Weisz, András György, Wei-I Lin, Devon Graham, Kevin Leyton-Brown, Csaba Szepesvari, Brendan Lucier

Algorithm configuration procedures optimize parameters of a given algorithm to perform well over a distribution of inputs.

Smarter Parking: Using AI to Identify Parking Inefficiencies in Vancouver

no code implementations • 21 Mar 2020 • Devon Graham, Satish Kumar Sarraf, Taylor Lundy, Ali MohammadMehr, Sara Uppal, Tae Yoon Lee, Hedayat Zarkoob, Scott Duke Kominers, Kevin Leyton-Brown

To see where this might be true in downtown Vancouver, we used artificial intelligence techniques to estimate the amount of time it would take drivers to both park on and off street for destinations throughout the city.

Equivariant Entity-Relationship Networks

1 code implementation • 21 Mar 2019 • Devon Graham, Junhao Wang, Siamak Ravanbakhsh

In this paper, we propose the Equivariant Entity-Relationship Network (EERN), which is a Multilayer Perceptron equivariant to the symmetry transformations of the Entity-Relationship model.

Knowledge Graphs

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

1 code implementation • NeurIPS 2019 • Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier, Devon Graham

Unfortunately, Structured Procrastination is not $\textit{adaptive}$ to characteristics of the parameterized algorithm: it treats every input like the worst case.