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
专题模式识别国家重点实验室_多媒体计算与图形学
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
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 下载所有文件
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 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yanbo Fan]的文章
[Ran He]的文章
[Jian Liang]的文章
百度学术
百度学术中相似的文章
[Yanbo Fan]的文章
[Ran He]的文章
[Jian Liang]的文章
必应学术
必应学术中相似的文章
[Yanbo Fan]的文章
[Ran He]的文章
[Jian Liang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Self-Paced Learning- an Implicit Regularization Perspective.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。