arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07002cs.LGstat.ML
收藏

双重双下降:线性回归任务间迁移学习的泛化误差

Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks

Rice University(莱斯大学)

Yehuda Dar, Richard G. Baraniuk

摘要:

研究了两个线性回归问题之间的迁移学习过程。一个重要的和及时的特殊情况是当回归器是过参数化的,并完美地插值其训练数据。我们研究了一个参数传输机制,其中目标任务解决方案的参数的一个子集被约束到一个相关的源任务学习的值。我们根据迁移学习架构中的突出因素来分析目标任务的泛化误差,即,可用示例的数量、每个任务中的(自由)参数的数量、从源任务传输到目标任务的参数的数量以及两个任务之间的关系。我们的非渐近分析表明,目标任务的泛化误差遵循二维双下降趋势(相对于每个任务中的自由参数的数量),这是由迁移学习因素控制。我们的分析指出了参数的转移作为额外的过度参数化的替代是有益的特定情况(即,目标任务中的附加自由参数)。具体来说,我们表明,迁移学习设置的有用性是脆弱的,并依赖于一组传输参数之间的微妙的相互作用,任务之间的关系,和真正的解决方案。我们还证明了当源任务与目标任务更接近或相同时,过度参数化的迁移学习不一定更有益。

英文摘要:

We study the transfer learning process between two linear regression problems. An important and timely special case is when the regressors are overparameterized and perfectly interpolate their training data. We examine a parameter transfer mechanism whereby a subset of the parameters of the target task solution are constrained to the values learned for a related source task. We analytically characterize the generalization error of the target task in terms of the salient factors in the transfer learning architecture, i.e., the number of examples available, the number of (free) parameters in each of the tasks, the number of parameters transferred from the source to target task, and the relation between the two tasks. Our non-asymptotic analysis shows that the generalization error of the target task follows a two-dimensional double descent trend (with respect to the number of free parameters in each of the tasks) that is controlled by the transfer learning factors. Our analysis points to specific cases where the transfer of parameters is beneficial as a substitute for extra overparameterization (i.e., additional free parameters in the target task). Specifically, we show that the usefulness of a transfer learning setting is fragile and depends on a delicate interplay among the set of transferred parameters, the relation between the tasks, and the true solution. We also demonstrate that overparameterized transfer learning is not necessarily more beneficial when the source task is closer or identical to the target task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑