GithubHelp home page GithubHelp logo

Comments (1)

ZhiningLiu1998 avatar ZhiningLiu1998 commented on July 28, 2024

你好,感谢提问。

首先,MESA的训练集不是train+valid,你可以仔细阅读论文中的算法2和算法3,其中D_t是train set,D_v是valid set。

  • train set: 算法2(ensemble training)的第7、8行描述了选取基学习器训练集的过程,你可以看到采样的是D_t,用于训练数据的是D_t的子集D'_t,i.e., D_v的数据并没用用于训练任何预测模型。
  • valid set: D_v在算法2(ensemble training)中只出现在4、5行,用于计算误差分布E_Dv和meta-state S_t,D_v在算法3(meta training)中只出现在line#6,用于计算reward(泛化性能的变化)。

你混淆了两个做法:“训练时使用train和valid” 和 “将train+valid作为训练集“

  • “训练时使用train和valid”:验证集本来的作用就是用来在训练的时候选取模型的最优设置,所以正常情况下的模型训练也会用到valid set。
  • 而你说的“将train+valid作为训练集“意味着不区分train+valid,直接把两者取并集作为train set扔给模型训练,这肯定是不对的。将valid set的内容放入训练集意味着用了训练集的一个子集选取超参数,这么做没有意义,并且如上所诉,也不是MESA的做法。

另:

  • 在meta-sampler的训练中使用了valid set的信息(比如用于计算meta-state和reward)用于指导teacher model什么是”good action“,但并没有直接从valid set数据特征直接学习信息(meta-sampler的输入空间是固定的状态空间,不是原始特征空间)。
  • 你可以将meta/teacher model的角色理解为调参的机器学习工程师,所以它们需要valid set的信息。在MESA论文的相关工作中有关meta learning的部分,你能找到更多元学习的工作,它们的teacher model也使用了valid set上的gradient,如[1][2]

[1] Mengye Ren, Wenyuan Zeng, Bin Yang, and Raquel Urtasun. Learning to reweight examples for robust deep learning. In International Conference on Machine Learning, pages 4334–4343, 2018.
[2] Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, and Deyu Meng. Meta-weight-net: Learning an explicit mapping for sample weighting. In NeurIPS, 2019.

from mesa.

Related Issues (9)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.