Fetching the paper…

Reading the bibliography…

2017

Learning with Changing Features

Dhurandhar, Amit, Hanneke, Steve, Yang, Liu

Original
PDF
Post on X

Understand

In this paper we study the setting where features are added or change interpretation over time, which has applications in multiple domains such as retail, manufacturing, finance.

In particular, we propose an approach to provably determine the time instant from which the new/changed features start becoming relevant with respect to an output variable in an agnostic (supervised) learning setting.
We also suggest an efficient version of our approach which has the same asymptotic performance.
Moreover, our theory also applies when we have more than one such change point.

Learning with Changing Features · Around

Built on

Estimation of Dependencies Based on Empirical Data
V. Vapnik · 1982
Earlier work this paper cites.
Convergence of Stochastic Processes
D. Pollard · 1984
Earlier work this paper cites.
Empirical Processes: Theory and Applications, Volume 2
D. Pollard · 1990
Earlier work this paper cites.
Detection of Abrupt Changes: Theory and Application
M. Basseville and I. V. Nikiforov · 1993
Earlier work this paper cites.
Statistical Learning Theory
V. Vapnik · 1998
Earlier work this paper cites.

Similar

Neural Network Learning: Theoretical Foundations
M. Anthony and P. L. Bartlett · 1999
Cited alongside, same era.
The covering number in learning theory
Original
D. X. Zhou · 2002
Cited alongside, same era.
Quickest Detection
H. V. Poor and O. Hadjiliadis · 2009
Cited alongside, same era.
A theory of learning from different domains
S. Ben-David, J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. Vaughan · 2010
Cited alongside, same era.
Regret minimization with concept drift
K. Crammer, Y. Mansour, E. Even-Dar, and J. Wortman Vaughan · 2010
Cited alongside, same era.

Then

Active learning with a drifting distribution
L. Yang · 2011
Later among the works it cites.
A survey on concept drift adaptation
J. Gama, I. Zliobaite, A. Bifet, M. Pechenizkiy, and A. Bouchachia · 2013
Later among the works it cites.
Efficient and accurate methods for updating generalized linear models with multiple feature additions
A. Dhurandhar and M. Petrik · 2014
Later among the works it cites.
Learning with a drifting target concept
S. Hanneke, V. Kanade, and L. Yang · 2015
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…