On Convergence Property of Implicit Self-paced Objective

نویسندگان

  • Zilu Ma
  • Shiqi Liu
  • Deyu Meng
چکیده

Self-paced learning (SPL) is a new methodology that simulates the learning principle of humans/animals to start learning easier aspects of a learning task, and then gradually take more complex examples into training. This new-coming learning regime has been empirically substantiated to be effective in various computer vision and pattern recognition tasks. Recently, it has been proved that the SPL regime has a close relationship to a implicit self-paced objective function. While this implicit objective could provide helpful interpretations to the effectiveness, especially the robustness, insights under the SPL paradigms, there are still no theoretical results strictly proved to verify such relationship. To this issue, in this paper, we provide some convergence results on this implicit objective of SPL. Specifically, we prove that the learning process of SPL always converges to critical points of this implicit objective under some mild conditions. This result verifies the intrinsic relationship between SPL and this implicit objective, and makes the previous robustness analysis on SPL complete and theoretically rational.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Next or Beyond Next: Effect of Contrastive Phrase-Based Treatment on Stage Gain Across Self-Paced and More Time-Constrained Tasks

This study explored the effect of contrastive phrase resynthesis instruction ongaining the teachability hypothesis stages in self-paced versus time-constrained oralproduction and recognition. Three groups (i.e., 23 learners) of high beginner femalelearners in an English language institute were randomly selected from a cohort oflearners. One group received contrastive metalinguistic instruction ...

متن کامل

Strong convergence of a general implicit algorithm for variational inequality problems and equilibrium problems and a continuous representation of nonexpansive mappings

We introduce a general implicit algorithm for finding a common element of‎ ‎the set of solutions of systems of equilibrium problems and the set of common fixed points‎ ‎of a sequence of nonexpansive mappings and a continuous representation of nonexpansive mappings‎. ‎Then we prove the strong convergence of the proposed implicit scheme to the unique solution of the minimization problem on the so...

متن کامل

Convergence theorems of implicit iterates with errors for generalized asymptotically quasi-nonexpansive mappings in Banach spaces

In this paper, we prove that an implicit iterative process with er-rors converges strongly to a common xed point for a nite family of generalizedasymptotically quasi-nonexpansive mappings on unbounded sets in a uniformlyconvex Banach space. Our results unify, improve and generalize the correspond-ing results of Ud-din and Khan [4], Sun [21], Wittman [23], Xu and Ori [26] andmany others.

متن کامل

Convergence theorems of an implicit iteration process for asymptotically pseudocontractive mappings

The purpose of this paper is to study the strong convergence of an implicit iteration process with errors to a common fixed point for a finite family of asymptotically pseudocontractive mappings and nonexpansive mappings in normed linear spaces. The results in this paper improve and extend the corresponding results of Xu and Ori, Zhou and Chang, Sun, Yang and Yu in some aspects.

متن کامل

Self-Paced Learning: An Implicit Regularization Perspective

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 functions. Existing methods usually pursue this by artificially designing the explicit form of regularizers. In this paper, we focus on the minimizer functions, and study a ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1703.09923  شماره 

صفحات  -

تاریخ انتشار 2017