paper-with-me

홈 › Papers

Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks

2018-02-11 · ICML 2018 7 · Daphna Weinshall, Gad Cohen, Dan Amir

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is monotonically increasing with the difficulty of the examples. Moreover, among all equally difficult points, convergence is faster when using points which incur higher loss with respect to the current hypothesis. We then analyze curriculum learning in the context of training a CNN. We describe a method which infers the curriculum by way of transfer learning from another network, pre-trained on a different task. While this approach can only approximate the ideal curriculum, we observe empirically similar behavior to the one predicted by the theory, namely, a significant boost in convergence speed at the beginning of training. When the task is made more difficult, improvement in generalization performance is also observed. Finally, curriculum learning exhibits robustness against unfavorable conditions such as excessive regularization.

📄 PDF Abstract BibTeX arXiv:1802.03796

Code (0)

등록된 구현이 없습니다.

Tasks

Learning TheoryTransfer Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics

2026-08-18 · Zhikai Ding, Ziyi Ye arxiv

Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies substantially across reasoning tasks, suggesting …

Understanding Curriculum Learning in Policy Optimization for Online Combinatorial Optimization

2022-02-11 · Runlong Zhou, Zelin He, Yuandong Tian, Yi Wu 외

Over the recent years, reinforcement learning (RL) starts to show promising results in tackling combinatorial optimization (CO) problems, in particular when coupled with curriculum learning to facilitate training. Despit…

Combinatorial OptimizationReinforcement Learning (RL)

Curriculum Meta-Learning for Next POI Recommendation

2021-08-14 · KDD 2021 8 · Yudong Chen, Xin Wang, Miao Fan, Jizhou Huang 외

Next point-of-interest (POI) recommendation is a hot research field where a recent emerging scenario, next POI to search recommendation, has been deployed in many online map services such as Baidu Maps. One of the key is…

Meta-Learning

Understanding Self-Paced Learning under Concave Conjugacy Theory

2018-05-21 · Shiqi Liu, Zilu Ma, Deyu Meng

By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests. However, …

Curriculum Design for Teaching via Demonstrations: Theory and Applications

2021-06-08 · NeurIPS 2021 12 · Gaurav Yengera, Rati Devidze, Parameswaran Kamalaruban, Adish Singla

We consider the problem of teaching via demonstrations in sequential decision-making settings. In particular, we study how to design a personalized curriculum over demonstrations to speed up the learner's convergence. We…

Decision MakingReinforcement Learning (RL)Sequential Decision Making