paper-with-me

Papers

Towards Black-box Iterative Machine Teaching

2017-10-21 · ICML 2018 7 · Weiyang Liu, Bo Dai, Xingguo Li, Zhen Liu, James M. Rehg, Le Song

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space machine teaching, where the teacher and the learner use different feature representations and the teacher can not fully observe the learner's model. In such scenario, we study how the teacher is still able to teach the learner to achieve faster convergence rate than the traditional passive learning. We propose an active teacher model that can actively query the learner (i.e., make the learner take exams) for estimating the learner's status and provably guide the learner to achieve faster convergence. The sample complexities for both teaching and query are provided. In the experiments, we compare the proposed active teacher with the omniscient teacher and verify the effectiveness of the active teacher model.

📄 PDF Abstract BibTeX arXiv:1710.07742

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Iterative Teaching by Data Hallucination

2022-10-31 · Zeju Qiu, Weiyang Liu, Tim Z. Xiao, Zhen Liu 외

We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i.e., a pool of finite samples), which greatly limits t…

Hallucination

Iterative Machine Teaching without Teachers

2020-06-27 · Mingzhe Yang, Yukino Baba

Iterative machine teaching is a method for selecting an optimal teaching example that enables a student to efficiently learn a target concept at each iteration. Existing studies on iterative machine teaching are based on…

Iterative Machine Teaching

2017-05-30 · ICML 2017 8 · Weiyang Liu, Bo Dai, Ahmad Humayun, Charlene Tay 외

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where…

Nonparametric Iterative Machine Teaching

2023-06-05 · Chen Zhang, Xiaofeng Cao, Weiyang Liu, Ivor Tsang 외

In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast convergence to a target model. However, ex…

Iterative Teaching by Label Synthesis

2021-10-27 · NeurIPS 2021 12 · Weiyang Liu, Zhen Liu, Hanchen Wang, Liam Paull 외

In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. In contrast to previous methods that have to scan over the enti…