> For the complete documentation index, see [llms.txt](https://lichangbin.gitbook.io/paper_notes/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lichangbin.gitbook.io/paper_notes/sep/learning-to-stop-while-learning-to-predict.md). # Learning to stop while learning to predict ICML2020 9-25-2020 ## Motivation * Task-imbalanced meta learning: different tasks need different numbers of gradient steps for adaptation * Deep learning based algorithms usually have a fixed number of iterations in the architecture. could we learn to stop automatically? ## Overview ![](https://1687130946-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-MEnQbUIupyAn8eMmrmG%2F-MIHiQuft0XG6NDwt6lW%2F-MIHn7TXAJZfUu2vMRR1%2Ff11.jpg?alt=media\&token=4035c9b5-c55e-4606-9819-f014bfcb5f29) * predictive model $$\mathcal{F}\_\theta$$ : transforms the input x to generate a path of states $$x\_1, x\_2, ...,x\_T$$ * stop policy $$\pi\_\phi$$ : sequentially observes the states $$x\_t$$ and determines the probability of stop at layer $$t$$ * variational stop time distribution $$q\_\phi$$ : stop time distribution induced by stopping policy $$\pi\_\phi$$ ![](https://1687130946-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-MEnQbUIupyAn8eMmrmG%2F-MIHoeSYZ4UY9jXgVaex%2F-MII4beOqxNSI_036r-M%2FLearn%20To%20Stop%20While%20To%20Predict-02.jpg?alt=media\&token=bbf96551-1596-4115-b0f7-1c95872f920c) ![](https://1687130946-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-MEnQbUIupyAn8eMmrmG%2F-MIHoeSYZ4UY9jXgVaex%2F-MII4etkJerQx9ot0qbV%2FLearn%20To%20Stop%20While%20To%20Predict-03.jpg?alt=media\&token=b18f6b20-aabc-4557-a41c-29d72284629c) ## Reference * * *