← Search

Sampath Kannan

2 accepted papers

2024

Oracle Efficient Algorithms for Groupwise Regret

ICLR 2024poster

We study the problem of online prediction, in which at each time step $t \in \{1,2, \cdots T\}$, an individual $x_t$ arrives, whose label we must predict. Each individual is associated with various groups, defined based on their features such as age, sex, race etc., which may intersect. Our goal is…

Cited by 3SourcePDFScholar
2018

A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem

NeurIPS 2018spotlight

Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to important decisions about individual people (such as criminal recidivism predictio…

Cited by 130SourcePDFScholar