# Nonparametric Teaching for Multiple Learners

Source: [Nonparametric Teaching for Multiple Learners](<https://www.sota2.com/research/paper/68fa71401e209131cea501a5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T04:23:44.437Z

Authors: Chen Zhang, Xiaofeng Cao, Weiyang Liu, Ivor Tsang, James Kwok

Published: 2023-11-17T04:04:11.000Z

## Abstract

We study the problem of teaching multiple learners simultaneously in the nonparametric iterative teaching setting, where the teacher iteratively provides examples to the learner for accelerating the acquisition of a target concept. This problem is motivated by the gap between current single-learner teaching setting and the real-world scenario of human instruction where a teacher typically imparts knowledge to multiple students. Under the new problem formulation, we introduce a novel framework -- Multi-learner Nonparametric Teaching (MINT). In MINT, the teacher aims to instruct multiple learners, with each learner focusing on learning a scalar-valued target model. To achieve this, we frame the problem as teaching a vector-valued target model and extend the target model space from a scalar-valued reproducing kernel Hilbert space used in single-learner scenarios to a vector-valued space. Furthermore, we demonstrate that MINT offers significant teaching speed-up over repeated single-learner teaching, particularly when the multiple learners can communicate with each other. Lastly, we conduct extensive experiments to validate the practicality and efficiency of MINT.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Reconstruction on Lion image RGB original (train)](<https://www.sota2.com/research/sota/image-reconstruction-on-lion-image-rgb-original-train.md>): Image Reconstruction; Lion image RGB original (train); PSNR: 22.75.

- [Image Reconstruction on Lion image RFT](<https://www.sota2.com/research/sota/image-reconstruction-on-lion-image-rft.md>): Image Reconstruction; Lion image RFT; PSNR: 20.19.

- [Image Reconstruction on Lion image (test)](<https://www.sota2.com/research/sota/image-reconstruction-on-lion-image-test.md>): Image Reconstruction; Lion image (test); PSNR: 20.03.

- [Image Reconstruction on Lion Image RGB (train)](<https://www.sota2.com/research/sota/image-reconstruction-on-lion-image-rgb-train.md>): Image Reconstruction; Lion Image RGB (train); PSNR: 24.58.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2311.10318>)

[PDF](<https://arxiv.org/pdf/2311.10318.pdf>)

[Implementation](<https://github.com/chen2hang/MINT_NonparametricTeaching>)