Teacher improves learning by selecting a training subset
Copyright 2018 by the author(s). We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better. We provide sharp super-teaching guarantees on two learners: the maximum likelihood estimator for the mean of a Gaussian, and the large margin...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2021
|
Online Access: | https://hdl.handle.net/1721.1/137038 |
_version_ | 1811089146901430272 |
---|---|
author | Ma, Y Nowak, R Rigollet, P Zhang, X Zhu, X |
author2 | Massachusetts Institute of Technology. Department of Mathematics |
author_facet | Massachusetts Institute of Technology. Department of Mathematics Ma, Y Nowak, R Rigollet, P Zhang, X Zhu, X |
author_sort | Ma, Y |
collection | MIT |
description | Copyright 2018 by the author(s). We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better. We provide sharp super-teaching guarantees on two learners: the maximum likelihood estimator for the mean of a Gaussian, and the large margin classifier in 1D. For general learners, we provide a mixed-integer nonlinear programming-based algorithm to find a super teaching set. Empirical experiments show that our algorithm is able to find good super-teaching sets for both regression and classification problems. |
first_indexed | 2024-09-23T14:14:26Z |
format | Article |
id | mit-1721.1/137038 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T14:14:26Z |
publishDate | 2021 |
record_format | dspace |
spelling | mit-1721.1/1370382023-02-10T20:33:27Z Teacher improves learning by selecting a training subset Ma, Y Nowak, R Rigollet, P Zhang, X Zhu, X Massachusetts Institute of Technology. Department of Mathematics Copyright 2018 by the author(s). We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better. We provide sharp super-teaching guarantees on two learners: the maximum likelihood estimator for the mean of a Gaussian, and the large margin classifier in 1D. For general learners, we provide a mixed-integer nonlinear programming-based algorithm to find a super teaching set. Empirical experiments show that our algorithm is able to find good super-teaching sets for both regression and classification problems. 2021-11-01T18:39:14Z 2021-11-01T18:39:14Z 2018 2021-05-26T13:09:34Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137038 Ma, Y, Nowak, R, Rigollet, P, Zhang, X and Zhu, X. 2018. "Teacher improves learning by selecting a training subset." International Conference on Artificial Intelligence and Statistics, AISTATS 2018, 84. en http://proceedings.mlr.press/v84/ma18a.html International Conference on Artificial Intelligence and Statistics, AISTATS 2018 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Proceedings of Machine Learning Research |
spellingShingle | Ma, Y Nowak, R Rigollet, P Zhang, X Zhu, X Teacher improves learning by selecting a training subset |
title | Teacher improves learning by selecting a training subset |
title_full | Teacher improves learning by selecting a training subset |
title_fullStr | Teacher improves learning by selecting a training subset |
title_full_unstemmed | Teacher improves learning by selecting a training subset |
title_short | Teacher improves learning by selecting a training subset |
title_sort | teacher improves learning by selecting a training subset |
url | https://hdl.handle.net/1721.1/137038 |
work_keys_str_mv | AT may teacherimproveslearningbyselectingatrainingsubset AT nowakr teacherimproveslearningbyselectingatrainingsubset AT rigolletp teacherimproveslearningbyselectingatrainingsubset AT zhangx teacherimproveslearningbyselectingatrainingsubset AT zhux teacherimproveslearningbyselectingatrainingsubset |