TY - JOUR
T1 - Multiclass performance metric elicitation
AU - Hiranandani, Gaurush
AU - Boodaghians, Shant
AU - Mehta, Ruta
AU - Koyejo, Oluwasanmi
N1 - Gaurush Hiranandani and Oluwasanmi Koyejo thank Microsoft Azure for providing computing credits. Shant Boodaghians and Ruta Mehta acknowledge the support of NSF via CCF 1750436.
PY - 2019
Y1 - 2019
N2 - Metric Elicitation is a principled framework for selecting the performance metric that best reflects implicit user preferences. However, available strategies have so far been limited to binary classification. In this paper, we propose novel strategies for eliciting multiclass classification performance metrics using only relative preference feedback. We also show that the strategies are robust to both finite sample and feedback noise.
AB - Metric Elicitation is a principled framework for selecting the performance metric that best reflects implicit user preferences. However, available strategies have so far been limited to binary classification. In this paper, we propose novel strategies for eliciting multiclass classification performance metrics using only relative preference feedback. We also show that the strategies are robust to both finite sample and feedback noise.
UR - http://www.scopus.com/inward/record.url?scp=85090171477&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090171477&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85090171477
SN - 1049-5258
VL - 32
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019
Y2 - 8 December 2019 through 14 December 2019
ER -