Author name cluster

Sechan Oh

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

2 author rows

UAI Conference 2017 Conference Paper

A Practical Method for Solving Contextual Bandit Problems Using Decision Trees

Adam N. Elmachtoub
Ryan McNellis
Sechan Oh
Marek Petrik

Many efficient algorithms with strong theoretical guarantees have been proposed for the contextual multi-armed bandit problem. However, applying these algorithms in practice can be difficult because they require domain expertise to build appropriate features and to tune their parameters. We propose a new method for the contextual bandit problem that is simple, practical, and can be applied with little or no domain expertise. Our algorithm relies on decision trees to model the context-reward relationship. Decision trees are non-parametric, interpretable, and work well without handcrafted features. To guide the explorationexploitation trade-off, we use a bootstrapping approach which abstracts Thompson sampling to non-Bayesian settings. We also discuss several computational heuristics and demonstrate the performance of our method on several datasets.

Details

AAAI Conference 2017 Conference Paper

Top-k Hierarchical Classification

Sechan Oh

This paper studies a top-k hierarchical classiﬁcation problem. In top-k classiﬁcation, one is allowed to make k predictions and no penalty is incurred if at least one of k predictions is correct. In hierarchical classiﬁcation, classes form a structured hierarchy, and misclassiﬁcation costs depend on the relation between the correct class and the incorrect class in the hierarchy. Despite that the fact that both top-k classiﬁcation and hierarchical classiﬁcation have gained increasing interests, the two problems have always been studied separately. In this paper, we deﬁne a top-k hierarchical loss function using a real world application. We provide the Bayes-optimal solution that minimizes the expected top-k hierarchical misclassiﬁcation cost. Via numerical experiments, we show that our solution outperforms two baseline methods that address only one of the two issues.

PDF Details