paper-with-me

Papers

Gradient Correction beyond Gradient Descent

2022-03-16 · Zefan Li, Bingbing Ni, Teng Li, Wenjun Zhang, Wen Gao

The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for back-propagation is apparently the most crucial aspect for the training of a neural network. The quality of the calculated gradient can be affected by multiple aspects, e.g., noisy data, calculation error, algorithm limitation, and so on. To reveal gradient information beyond gradient descent, we introduce a framework (\textbf{GCGD}) to perform gradient correction. GCGD consists of two plug-in modules: 1) inspired by the idea of gradient prediction, we propose a \textbf{GC-W} module for weight gradient correction; 2) based on Neural ODE, we propose a \textbf{GC-ODE} module for hidden states gradient correction. Experiment results show that our gradient correction framework can effectively improve the gradient quality to reduce training epochs by $\sim$ 20\% and also improve the network performance.

📄 PDF Abstract BibTeX arXiv:2203.08345

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

EXACT ANALYSIS OF CURVATURE CORRECTED LEARNING DYNAMICS IN DEEP LINEAR NETWORKS

2019-09-25 · Dongsung Huh

Deep neural networks exhibit complex learning dynamics due to the highly non-convex loss landscape, which causes slow convergence and vanishing gradient problems. Second order approaches, such as natural gradient descent…

Second-order methods

Gradient descent inference in empirical risk minimization

2024-12-12 · Qiyang Han, Xiaocong Xu

Gradient descent is one of the most widely used iterative algorithms in modern statistical learning. However, its precise algorithmic dynamics in high-dimensional settings remain only partially understood, which has ther…

IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback

2026-05-12 · Benjamin Amoh, Geoffrey G. Parker, Wesley Marrero arxiv

Decision-focused learning trains predictive models end-to-end against downstream decision loss, but online settings suffer delayed feedback: outcomes may not arrive for many environment interactions. We identify \emph{st…

Bilevel Optimization

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features

2024-02-12 · Rodrigo Veiga, Anastasia Remizova, Nicolas Macris

We investigate the test risk of continuous-time stochastic gradient flow dynamics in learning theory. Using a path integral formulation we provide, in the regime of a small learning rate, a general formula for computing …

Learning Theory

Curvature-corrected learning dynamics in deep neural networks

2020-01-01 · ICML 2020 1 · Dongsung Huh

Deep neural networks exhibit highly non-convex loss landscape, which results in complex learning dynamics under steepest gradient descent. Second order optimization methods, such as natural gradient descent, can facilita…

Second-order methods