Teacher Improves Learning by Selecting a Training Subset
By Robert D. Nowak, Philippe Rigollet, Xuezhou Zhang, Xiaojin Zhu. 2018
16 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jy-yong Sohn
- Dimitris Papailiopoulos
- Hongyi Wang
- Shashank Rajput
- Saurabh Agarwal
- Kangwook Lee
- Harit Vishwakarma
- Kartik K. Sreenivasan
In Computer Vision and Pattern Recognition
- Shashank Rajput
- Dimitris Papailiopoulos
- Hongyi Wang
- Saurabh Agarwal
- Kangwook Lee
- Harit Vishwakarma
- Kartik K. Sreenivasan
- Jy-yong Sohn
Citations in the corpus
- Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020, methodology): “It is typically used to speed up training [59, 60, 61] by choosing the optimal training sequence.”