Angle based dynamic learning rate for gradient descent

• URL: http://arxiv.org/abs/2304.10457v1
• Date: Thu, 20 Apr 2023 16:55:56 GMT
• Title: Angle based dynamic learning rate for gradient descent
• Authors: Neel Mishra, Pawan Kumar
• Abstract summary: We propose a novel yet simple approach to obtain an adaptive learning rate for gradient-based descent methods on classification tasks. Instead of the traditional approach of selecting adaptive learning rates via the expectation of gradient-based terms, we use the angle between the current gradient and the new gradient. We find that our method leads to the highest accuracy in most of the datasets.
• Score: 2.5077510176642805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In our work, we propose a novel yet simple approach to obtain an adaptive learning rate for gradient-based descent methods on classification tasks. Instead of the traditional approach of selecting adaptive learning rates via the decayed expectation of gradient-based terms, we use the angle between the current gradient and the new gradient: this new gradient is computed from the direction orthogonal to the current gradient, which further helps us in determining a better adaptive learning rate based on angle history, thereby, leading to relatively better accuracy compared to the existing state-of-the-art optimizers. On a wide variety of benchmark datasets with prominent image classification architectures such as ResNet, DenseNet, EfficientNet, and VGG, we find that our method leads to the highest accuracy in most of the datasets. Moreover, we prove that our method is convergent.

Related papers

• Gradient-Variation Online Learning under Generalized Smoothness [56.38427425920781]
  gradient-variation online learning aims to achieve regret guarantees that scale with variations in gradients of online functions. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. We provide the applications for fast-rate convergence in games and extended adversarial optimization.
  arXiv  Detail & Related papers  (2024-08-17T02:22:08Z)
• Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation [15.791041311313448]
  gradient alignment-based Test-time adaptation (GraTa) method to improve gradient direction and learning rate. GraTa method incorporates an auxiliary gradient with the pseudo one to facilitate gradient alignment. Design a dynamic learning rate based on the cosine similarity between the pseudo and auxiliary gradients.
  arXiv  Detail & Related papers  (2024-08-14T07:37:07Z)
• Interpreting Adaptive Gradient Methods by Parameter Scaling for Learning-Rate-Free Optimization [14.009179786857802]
  We address the challenge of estimating the learning rate for adaptive gradient methods used in training deep neural networks. While several learning-rate-free approaches have been proposed, they are typically tailored for steepest descent. In this paper, we interpret adaptive gradient methods as steepest descent applied on parameter-scaled networks.
  arXiv  Detail & Related papers  (2024-01-06T15:45:29Z)
• Neural Gradient Learning and Optimization for Oriented Point Normal Estimation [53.611206368815125]
  We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
  arXiv  Detail & Related papers  (2023-09-17T08:35:11Z)
• Scaling Forward Gradient With Local Losses [117.22685584919756]
  Forward learning is a biologically plausible alternative to backprop for learning deep neural networks. We show that it is possible to substantially reduce the variance of the forward gradient by applying perturbations to activations rather than weights. Our approach matches backprop on MNIST and CIFAR-10 and significantly outperforms previously proposed backprop-free algorithms on ImageNet.
  arXiv  Detail & Related papers  (2022-10-07T03:52:27Z)
• Delving into Effective Gradient Matching for Dataset Condensation [13.75957901381024]
  gradient matching method directly targets the training dynamics by matching the gradient when training on the original and synthetic datasets. We propose to match the multi-level gradients to involve both intra-class and inter-class gradient information. An overfitting-aware adaptive learning step strategy is also proposed to trim unnecessary optimization steps for algorithmic efficiency improvement.
  arXiv  Detail & Related papers  (2022-07-30T21:31:10Z)
• Incorporating the Barzilai-Borwein Adaptive Step Size into Sugradient Methods for Deep Network Training [3.8762085568003406]
  We adapt the learning rate using a two-point approximation to the secant equation which quasi-Newton methods are based upon. We evaluate our method using standard example network architectures on widely available datasets and compare against alternatives elsewhere in the literature.
  arXiv  Detail & Related papers  (2022-05-27T02:12:59Z)
• Continuous-Time Meta-Learning with Forward Mode Differentiation [65.26189016950343]
  We introduce Continuous Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous. We show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.
  arXiv  Detail & Related papers  (2022-03-02T22:35:58Z)
• Channel-Directed Gradients for Optimization of Convolutional Neural Networks [50.34913837546743]
  We introduce optimization methods for convolutional neural networks that can be used to improve existing gradient-based optimization in terms of generalization error. We show that defining the gradients along the output channel direction leads to a performance boost, while other directions can be detrimental.
  arXiv  Detail & Related papers  (2020-08-25T00:44:09Z)
• Disentangling Adaptive Gradient Methods from Learning Rates [65.0397050979662]
  We take a deeper look at how adaptive gradient methods interact with the learning rate schedule. We introduce a "grafting" experiment which decouples an update's magnitude from its direction. We present some empirical and theoretical retrospectives on the generalization of adaptive gradient methods.
  arXiv  Detail & Related papers  (2020-02-26T21:42:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.