paper-with-me

홈 › Papers

Improving Layer-wise Adaptive Rate Methods using Trust Ratio Clipping

2020-11-27 · Jeffrey Fong, Siwei Chen, Kaiqi Chen

Training neural networks with large batch is of fundamental significance to deep learning. Large batch training remarkably reduces the amount of training time but has difficulties in maintaining accuracy. Recent works have put forward optimization methods such as LARS and LAMB to tackle this issue through adaptive layer-wise optimization using trust ratios. Though prevailing, such methods are observed to still suffer from unstable and extreme trust ratios which degrades performance. In this paper, we propose a new variant of LAMB, called LAMBC, which employs trust ratio clipping to stabilize its magnitude and prevent extreme values. We conducted experiments on image classification tasks such as ImageNet and CIFAR-10 and our empirical results demonstrate promising improvements across different batch sizes.

📄 PDF Abstract BibTeX arXiv:2011.13584

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

LARS Layer-wise Adaptive Rate Scaling, or LARS, is a large batch optimization technique. There are two notable differences between LARS and other adaptive algorithms such as…
Adam 설명 없음
LAMB LAMB is a a layerwise adaptive large batch optimization technique. It provides a strategy for adapting the learning rate in large batch settings. LAMB uses…

Similar Papers 제목 키워드 기반

Adaptive Hypergraph Network for Trust Prediction

2024-02-07 · Rongwei Xu, Guanfeng Liu, Yan Wang, Xuyun Zhang 외

Trust plays an essential role in an individual's decision-making. Traditional trust prediction models rely on pairwise correlations to infer potential relationships between users. However, in the real world, interactions…

Contrastive LearningDecision MakingPrediction

OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling

2026-05-08 · Yuxuan Lou, Yang You arxiv

Muon improves neural-network training by orthogonalizing matrix-valued updates, but it leaves each layer's update magnitude controlled mostly by a global learning rate. We introduce OrScale, a trust-ratio extension of Mu…

FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity

2026-07-04 · Shuai Li, Qinglin Wang, Ping Luo, Jiahuan Wang 외 arxiv

Federated Transformer training increasingly relies on local AdamW, whose adaptive updates can provide much stronger local progress than SGD-based training. However, under heterogeneous client data, even globally correcte…

GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning

2026-04-09 · Kaiyuan Tian, Yu Tang, Gongqingjian Jiang, Baihui Liu 외 arxiv

Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these appro…

KGTrust: Evaluating Trustworthiness of SIoT via Knowledge Enhanced Graph Neural Networks

2023-02-22 · Zhizhi Yu, Di Jin, Cuiying Huo, Zhiqiang Wang 외

Social Internet of Things (SIoT), a promising and emerging paradigm that injects the notion of social networking into smart objects (i.e., things), paving the way for the next generation of Internet of Things. However, d…

Graph Neural Network