paper-with-me

홈 › Papers

ADLER -- An efficient Hessian-based strategy for adaptive learning rate

2023-05-25 · Dario Balboni, Davide Bacciu

We derive a sound positive semi-definite approximation of the Hessian of deep models for which Hessian-vector products are easily computable. This enables us to provide an adaptive SGD learning rate strategy based on the minimization of the local quadratic approximation, which requires just twice the computation of a single SGD run, but performs comparably with grid search on SGD learning rates on different model architectures (CNN with and without residual connections) on classification tasks. We also compare the novel approximation with the Gauss-Newton approximation.

📄 PDF Abstract BibTeX arXiv:2305.16396

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning

2025-04-16 · Yuan Luo, Rudolf Hoffmann, Yan Xia, Olaf Wysocki 외

Semantic 3D city models are worldwide easy-accessible, providing accurate, object-oriented, and semantic-rich 3D priors. To date, their potential to mitigate the noise impact on radar object detection remains under-explo…

Objectobject-detectionObject DetectionRadar Object Detection+1

AdLER: Adversarial Training with Label Error Rectification for One-Shot Medical Image Segmentation

2023-09-02 · Xiangyu Zhao, Sheng Wang, Zhiyun Song, Zhenrong Shen 외

Accurate automatic segmentation of medical images typically requires large datasets with high-quality annotations, making it less applicable in clinical settings due to limited training data. One-shot segmentation based …

AnatomyData AugmentationDiversityImage Segmentation+4

AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling

2025-05-27 · Ganglou Xu

Federated learning faces critical challenges in balancing communication efficiency and model accuracy. One key issue lies in the approximation of update errors without incurring high computational costs. In this paper, w…

Federated Learning

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning

2020-06-01 · Zhewei Yao, Amir Gholami, Sheng Shen, Mustafa Mustafa 외

We introduce ADAHESSIAN, a second order stochastic optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates of the HESSIAN. Second order algorithms are among the mos…

BIG-bench Machine LearningSecond-order methodsStochastic Optimization

BaKron: Efficient Quantization with Kronecker-Factored Hessians

2026-08-06 · Johann Birnick, Rayan Saab arxiv

We accelerate a family of algorithms for neural network quantization whose geometry is informed by any Kronecker-factored approximation of the Hessian. GPTQ-style adaptive rounding typically uses one-sided information de…