Loading...
conference paper
Computable Bounds on the Exploration Bias
2018
Proceedings of the 2018 IEEE International Symposium on Information Theory (ISIT)
Adaptive data analysis is known to introduce bias in reported measurements. Russo and Zou [1] recently introduced an information-theoretic framework to study this problem. Herein, this framework is adopted and new dependence measures are introduced to bound the exploration bias. When the measurements have bounded L1− or L2 -norms, or when the selection procedure is symmetric, the new bounds are such that the contribution of the selection procedure to the bias is decoupled from the effects of the underlying distribution generating the data, thus enabling direct comparisons between different selection procedures.
Type
conference paper
Authors
Publication date
2018
Published in
Proceedings of the 2018 IEEE International Symposium on Information Theory (ISIT)
Start page
576
End page
580
Peer reviewed
REVIEWED
EPFL units
Event name | Event place | Event date |
Vail, CO, USA | June 17-22, 2018 | |
Available on Infoscience
August 21, 2018
Use this identifier to reference this record