paper-with-me

Papers

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 updating process of the parameter and the learning rate into a maxmin problem. Some existing schemes such as AdaGrad (diagonal version) and WNGrad can be rederived from our approach. Based on our approach, the updating rules for the learning rate do not rely on the smoothness constant of optimization problems and are robust to the initial learning rate. We theoretically analyze our approach in full batch and online learning settings, which achieves comparable performances with other first-order gradient-based algorithms in terms of accuracy as well as convergence rate.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…

Similar Papers 제목 키워드 기반

ZENITH: Automated Gradient Norm Informed Stochastic Optimization

2026-01-21 · Dhrubo Saha arxiv

Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule. While existing adaptive optimizers schedule the LR automatically, they suffer from computational…

Stochastic OptimizationInstance SegmentationImage ClassificationKeypoint Detection

Stable Weight Decay Regularization

2020-09-28 · Zeke Xie, Issei Sato, Masashi Sugiyama

Weight decay is a popular regularization technique for training of deep neural networks. Modern deep learning libraries mainly use $L_{2}$ regularization as the default implementation of weight decay. \citet{loshchilov20…

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…

Improving Robustness with Adaptive Weight Decay

2022-09-30 · NeurIPS 2023 11 · Amin Ghiasi, Ali Shafahi, Reza Ardekani

We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration. For classification problems, we propose changing the value of the weight decay hyper-parame…

Adversarial Robustness

Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks

2019-04-30 · NeurIPS 2019 12 · Gauthier Gidel, Francis Bach, Simon Lacoste-Julien

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-paramet…