Timezone: »

Consistency Analysis for Binary Classification Revisited
Krzysztof Dembczynski · Wojciech Kotlowski · Sanmi Koyejo · Nagarajan Natarajan

Mon Aug 07 09:42 PM -- 10:00 PM (PDT) @ C4.8

Statistical learning theory is at an inflection point enabled by recent advances in understanding and optimizing a wide range of metrics. Of particular interest are non-decomposable metrics such as the F-measure and the Jaccard measure which cannot be represented as a simple average over examples. Non-decomposability is the primary source of difficulty in theoretical analysis, and interestingly has led to two distinct settings and notions of consistency. In this manuscript we analyze both settings, from statistical and algorithmic points of view, to explore the connections and to highlight differences between them for a wide range of metrics. The analysis complements previous results on this topic, clarifies common confusions around both settings, and provides guidance to the theory and practice of binary classification with complex metrics.

Author Information

Krzysztof Dembczynski (Poznan University of Technology)

Krzysztof Dembczyński is an assistant professor at Poznań University of Technology. He received his B.Sc., M.Sc., and Ph.D. degrees in computer science from the same university. As a post-doctoral researcher he spent two years from 2009 to 2011 in the Knowledge Engineering & Bioinformatics Lab at Marburg University, Germany. His articles have been published at the main conferences (ECML,ICML, NIPS) and in the leading journals (JMLR, MLJ, DAMI) in the field of machine learning. As a co-author he won the best paper award at the European Conference on Artificial Intelligence 2012 and at the Asian Conference on Machine Learning 2015. He also gave a tutorial on multi-target prediction problems at the International Conference on Machine Learning 2013 and at Algorithmic Learning Theory/Discovery Science 2013. He serves as a member of the program committees of major conferences in the field of artificial intelligence (ICML, NIPS, IJCAI, AAAI, KDD) and as a reviewer for several international journals (MLJ, DAMI, JMLR). He is a laureate of a prestigious scholarship in the HOMING PLUS programme awarded by the Foundation for Polish Science (2012– 2014). He was also receiving a stipend for outstanding young scientists funded by the Polish Ministry of Science and Higher Education (2011–2013).

Wojciech Kotlowski (Poznan University of Technology)
Sanmi Koyejo (University of Illinois at Urbana-Champaign)
Sanmi Koyejo

Sanmi (Oluwasanmi) Koyejo is an Assistant Professor in the Department of Computer Science at Stanford University. Koyejo was previously an Associate Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign. Koyejo's research interests are in developing the principles and practice of trustworthy machine learning, focusing on applications to neuroscience and healthcare. Koyejo completed a Ph.D. in Electrical Engineering at the University of Texas at Austin, advised by Joydeep Ghosh, and postdoctoral research at Stanford University with Russell A. Poldrack and Pradeep Ravikumar. Koyejo has been the recipient of several awards, including a best paper award from the conference on uncertainty in artificial intelligence, a Skip Ellis Early Career Award, a Sloan Fellowship, a Terman faculty fellowship, an NSF CAREER award, a Kavli Fellowship, an IJCAI early career spotlight, and a trainee award from the Organization for Human Brain Mapping. Koyejo spends time at Google as a part of the Brain team, serves on the Neural Information Processing Systems Foundation Board, the Association for Health Learning and Inference Board, and as president of the Black in AI organization.

Nagarajan Natarajan (Microsoft Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors