paper-with-me

홈 › Papers

When Do Flat Minima Optimizers Work?

2022-02-01 · Jean Kaddour, Linqing Liu, Ricardo Silva, Matt J. Kusner

Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers. Two methods have received significant attention due to their scalability: 1. Stochastic Weight Averaging (SWA), and 2. Sharpness-Aware Minimization (SAM). However, there has been limited investigation into their properties and no systematic benchmarking of them across different domains. We fill this gap here by comparing the loss surfaces of the models trained with each method and through broad benchmarking across computer vision, natural language processing, and graph representation learning tasks. We discover several surprising findings from these results, which we hope will help researchers further improve deep learning optimizers, and practitioners identify the right optimizer for their problem.

📄 PDF Abstract BibTeX arXiv:2202.00661

Code (1)

JeanKaddour/WASAM 공식 구현 pytorch

Tasks

BenchmarkingGraph LearningGraph Representation LearningImage ClassificationKnowledge GraphsLink PredictionNatural Language InferenceNatural Language UnderstandingNode ClassificationNode Property PredictionQuestion AnsweringRepresentation LearningSelf-Supervised Image Classification

Methods 이 논문이 사용한 방법론

Sharpness-Aware Minimization Sharpness-Aware Minimization, or SAM, is a procedure that improves model generalization by simultaneously minimizing loss value and loss sharpness. SAM functions by…
Stochastic Weight Averaging Stochastic Weight Averaging is an optimization procedure that averages multiple points along the trajectory of SGD, with a cyclical or…

Similar Papers 제목 키워드 기반

Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization

2023-03-03 · CVPR 2023 1 · Xingxuan Zhang, Renzhe Xu, Han Yu, Hao Zou 외

Recently, flat minima are proven to be effective for improving generalization and sharpness-aware minimization (SAM) achieves state-of-the-art performance. Yet the current definition of flatness discussed in SAM and its …

C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning

2025-08-26 · Wei Li, Hangjie Yuan, Zixiang Zhao, Yifan Zhu 외 arxiv

Balancing sensitivity to new tasks and stability for retaining past knowledge is crucial in continual learning (CL). Recently, sharpness-aware minimization has proven effective in transfer learning and has also been adop…

Continual LearningTransfer Learning

Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms

2024-03-01 · Toki Tahmid Inan, Mingrui Liu, Amarda Shehu

Despite an extensive body of literature on deep learning optimization, our current understanding of what makes an optimization algorithm effective is fragmented. In particular, we do not understand well whether enhanced …

BenchmarkingStochastic Optimization

Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models

2022-10-25 · Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as …

Language ModelingLanguage Modelling

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term

2023-05-25 · Yun Yue, Jiadi Jiang, Zhiling Ye, Ning Gao 외

Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization. …