paper-with-me

홈 › Papers

Meta-Regularization: An Approach to Adaptive Choice of the Learning Rate in Gradient Descent

2021-04-12 · Guangzeng Xie, Hao Jin, Dachao Lin, Zhihua Zhang

We propose \textit{Meta-Regularization}, a novel approach for the adaptive choice of the learning rate in first-order gradient descent methods. Our approach modifies the objective function by adding a regularization term on the learning rate, and casts the joint updating process of parameters and learning rates into a maxmin problem. Given any regularization term, our approach facilitates the generation of practical algorithms. When \textit{Meta-Regularization} takes the $\varphi$-divergence as a regularizer, the resulting algorithms exhibit comparable theoretical convergence performance with other first-order gradient-based algorithms. Furthermore, we theoretically prove that some well-designed regularizers can improve the convergence performance under the strong-convexity condition of the objective function. Numerical experiments on benchmark problems demonstrate the effectiveness of algorithms derived from some common $\varphi$-divergence in full batch as well as online learning settings.

📄 PDF Abstract BibTeX arXiv:2104.05447

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning

2026-05-18 · Ankita Awasthi, Marco Apolinario, Kaushik Roy arxiv

In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This contrasts sharply with off-line continu…

Class Incremental LearningContinual Learning

Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification

2022-09-10 · COLING 2022 10 · Tianyi Lei, Honghui Hu, Qiaoyang Luo, Dezhong Peng 외

Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching…

Few-Shot Text ClassificationMeta-Learningtext-classificationText Classification

Hyper-Regularization: An Adaptive Choice for the Learning Rate in Gradient Descent

2019-05-01 · ICLR 2019 5 · Guangzeng Xie, Hao Jin, Dachao Lin, Zhihua Zhang

We present a novel approach for adaptively selecting the learning rate in gradient descent methods. Specifically, we impose a regularization term on the learning rate via a generalized distance, and cast the joint updat…

Adaptive regularization for Lasso models in the context of non-stationary data streams

2016-10-28 · Ricardo Pio Monti, Christoforos Anagnostopoulos, Giovanni Montana

Large scale, streaming datasets are ubiquitous in modern machine learning. Streaming algorithms must be scalable, amenable to incremental training and robust to the presence of non-stationarity. In this work consider the…

Cooperative Meta-Learning with Gradient Augmentation

2024-06-07 · Jongyun Shin, Seunjin Han, Jangho Kim

Model agnostic meta-learning (MAML) is one of the most widely used gradient-based meta-learning, consisting of two optimization loops: an inner loop and outer loop. MAML learns the new task from meta-initialization param…

Few-Shot Image Classificationimage-classificationImage ClassificationMeta-Learning+1