Nonparametric Indirect Active Learning

Shashank Singh
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:2515-2541, 2023.

Abstract

Typical models of active learning assume a learner can directly manipulate or query a covariate X to study its relationship with a response Y. However, if X is a feature of a complex system, it may be possible only to indirectly influence X by manipulating a control variable Z, a scenario we refer to as Indirect Active Learning. Under a nonparametric fixed-budget model of Indirect Active Learning, we study minimax convergence rates for estimating a local relationship between X and Y, with different rates depending on the complexities and noise levels of the relationships between Z and X and between X and Y. We also derive minimax rates for passive learning under comparable assumptions, finding in many cases that, while there is an asymptotic benefit to active learning, this benefit is fully realized by a simple two-stage learner that runs two passive experiments in sequence.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-singh23a, title = {Nonparametric Indirect Active Learning}, author = {Singh, Shashank}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {2515--2541}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/singh23a/singh23a.pdf}, url = {https://proceedings.mlr.press/v206/singh23a.html}, abstract = {Typical models of active learning assume a learner can directly manipulate or query a covariate X to study its relationship with a response Y. However, if X is a feature of a complex system, it may be possible only to indirectly influence X by manipulating a control variable Z, a scenario we refer to as Indirect Active Learning. Under a nonparametric fixed-budget model of Indirect Active Learning, we study minimax convergence rates for estimating a local relationship between X and Y, with different rates depending on the complexities and noise levels of the relationships between Z and X and between X and Y. We also derive minimax rates for passive learning under comparable assumptions, finding in many cases that, while there is an asymptotic benefit to active learning, this benefit is fully realized by a simple two-stage learner that runs two passive experiments in sequence.} }
Endnote
%0 Conference Paper %T Nonparametric Indirect Active Learning %A Shashank Singh %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-singh23a %I PMLR %P 2515--2541 %U https://proceedings.mlr.press/v206/singh23a.html %V 206 %X Typical models of active learning assume a learner can directly manipulate or query a covariate X to study its relationship with a response Y. However, if X is a feature of a complex system, it may be possible only to indirectly influence X by manipulating a control variable Z, a scenario we refer to as Indirect Active Learning. Under a nonparametric fixed-budget model of Indirect Active Learning, we study minimax convergence rates for estimating a local relationship between X and Y, with different rates depending on the complexities and noise levels of the relationships between Z and X and between X and Y. We also derive minimax rates for passive learning under comparable assumptions, finding in many cases that, while there is an asymptotic benefit to active learning, this benefit is fully realized by a simple two-stage learner that runs two passive experiments in sequence.
APA
Singh, S.. (2023). Nonparametric Indirect Active Learning. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:2515-2541 Available from https://proceedings.mlr.press/v206/singh23a.html.

Related Material