Open Problem: Property Elicitation and Elicitation Complexity

Rafael Frongillo, Ian Kash, Stephen Becker
; 29th Annual Conference on Learning Theory, PMLR 49:1655-1658, 2016.

Abstract

The study of property elicitation is gaining ground in statistics and machine learning as a way to view and reason about the expressive power of emiprical risk minimization (ERM). Yet beyond a widening frontier of special cases, the two most fundamental questions in this area remain open: which statistics are elicitable (computable via ERM), and which loss functions elicit them? Moreover, recent work suggests a complementary line of questioning: given a statistic, how many ERM parameters are needed to compute it? We give concrete instantiations of these important questions, which have numerous applications to machine learning and related fields.

Cite this Paper


BibTeX
@InProceedings{pmlr-v49-frongillo16, title = {Open Problem: Property Elicitation and Elicitation Complexity}, author = {Rafael Frongillo and Ian Kash and Stephen Becker}, booktitle = {29th Annual Conference on Learning Theory}, pages = {1655--1658}, year = {2016}, editor = {Vitaly Feldman and Alexander Rakhlin and Ohad Shamir}, volume = {49}, series = {Proceedings of Machine Learning Research}, address = {Columbia University, New York, New York, USA}, month = {23--26 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v49/frongillo16.pdf}, url = {http://proceedings.mlr.press/v49/frongillo16.html}, abstract = {The study of property elicitation is gaining ground in statistics and machine learning as a way to view and reason about the expressive power of emiprical risk minimization (ERM). Yet beyond a widening frontier of special cases, the two most fundamental questions in this area remain open: which statistics are elicitable (computable via ERM), and which loss functions elicit them? Moreover, recent work suggests a complementary line of questioning: given a statistic, how many ERM parameters are needed to compute it? We give concrete instantiations of these important questions, which have numerous applications to machine learning and related fields.} }
Endnote
%0 Conference Paper %T Open Problem: Property Elicitation and Elicitation Complexity %A Rafael Frongillo %A Ian Kash %A Stephen Becker %B 29th Annual Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2016 %E Vitaly Feldman %E Alexander Rakhlin %E Ohad Shamir %F pmlr-v49-frongillo16 %I PMLR %J Proceedings of Machine Learning Research %P 1655--1658 %U http://proceedings.mlr.press %V 49 %W PMLR %X The study of property elicitation is gaining ground in statistics and machine learning as a way to view and reason about the expressive power of emiprical risk minimization (ERM). Yet beyond a widening frontier of special cases, the two most fundamental questions in this area remain open: which statistics are elicitable (computable via ERM), and which loss functions elicit them? Moreover, recent work suggests a complementary line of questioning: given a statistic, how many ERM parameters are needed to compute it? We give concrete instantiations of these important questions, which have numerous applications to machine learning and related fields.
RIS
TY - CPAPER TI - Open Problem: Property Elicitation and Elicitation Complexity AU - Rafael Frongillo AU - Ian Kash AU - Stephen Becker BT - 29th Annual Conference on Learning Theory PY - 2016/06/06 DA - 2016/06/06 ED - Vitaly Feldman ED - Alexander Rakhlin ED - Ohad Shamir ID - pmlr-v49-frongillo16 PB - PMLR SP - 1655 DP - PMLR EP - 1658 L1 - http://proceedings.mlr.press/v49/frongillo16.pdf UR - http://proceedings.mlr.press/v49/frongillo16.html AB - The study of property elicitation is gaining ground in statistics and machine learning as a way to view and reason about the expressive power of emiprical risk minimization (ERM). Yet beyond a widening frontier of special cases, the two most fundamental questions in this area remain open: which statistics are elicitable (computable via ERM), and which loss functions elicit them? Moreover, recent work suggests a complementary line of questioning: given a statistic, how many ERM parameters are needed to compute it? We give concrete instantiations of these important questions, which have numerous applications to machine learning and related fields. ER -
APA
Frongillo, R., Kash, I. & Becker, S.. (2016). Open Problem: Property Elicitation and Elicitation Complexity. 29th Annual Conference on Learning Theory, in PMLR 49:1655-1658

Related Material