Knowledge Commons of Institute of Automation,CAS
Self-Paced Learning: An Implicit Regularization Perspective | |
Yanbo Fan1,4; Ran He1,2,3,4; Jian Liang1,2,4; Baogang Hu1,4 | |
2017 | |
会议名称 | American Association for AI National Conference(AAAI) |
会议日期 | 2017 |
会议地点 | San Francisco, California USA |
摘要 |
Self-paced learning (SPL) mimics the cognitive mechanism of humans and animals that gradually learns from easy to hard samples. One key issue in SPL is to obtain better weighting strategy that is determined by the minimizer function. Existing
methods usually pursue this by artificially designing the explicit form of SPL regularizer. In this paper, we study a group of new regularizer (named self-paced implicit regularizer)
that is deduced from robust loss function. Based on the convex conjugacy theory, the minimizer function for selfpaced implicit regularizer can be directly learned from the
latent loss function, while the analytic form of the regularizer can be even unknown. A general framework (named SPL-IR) for SPL is developed accordingly. We demonstrate that the learning procedure of SPL-IR is associated with latent robust loss functions, thus can provide some theoretical insights for its working mechanism. We further analyze the relation between SPL-IR and half-quadratic optimization and provide a group of self-paced implicit regularizer. Finally, we implement SPL-IR to both supervised and unsupervised asks, and experimental results corroborate our ideas and demonstrate the correctness and effectiveness of implicit regularizers. |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/19999 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
作者单位 | 1.National Laboratory of Pattern Recognition, CASIA 2.Center for Research on Intelligent Perception and Computing, CASIA 3.Center for Excellence in Brain Science and Intelligence Technology, CAS 4.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yanbo Fan,Ran He,Jian Liang,et al. Self-Paced Learning: An Implicit Regularization Perspective[C],2017. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Self-Paced Learning-(890KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论