paper-with-me

홈 › Papers

PFGE: Parsimonious Fast Geometric Ensembling of DNNs

2022-02-14 · Hao Guo, Jiyong Jin, Bin Liu

Ensemble methods are commonly used to enhance the generalization performance of machine learning models. However, they present a challenge in deep learning systems due to the high computational overhead required to train an ensemble of deep neural networks (DNNs). Recent advancements such as fast geometric ensembling (FGE) and snapshot ensembles have addressed this issue by training model ensembles in the same time as a single model. Nonetheless, these techniques still require additional memory for test-time inference compared to single-model-based methods. In this paper, we propose a new method called parsimonious FGE (PFGE), which employs a lightweight ensemble of higher-performing DNNs generated through successive stochastic weight averaging procedures. Our experimental results on CIFAR-{10,100} and ImageNet datasets across various modern DNN architectures demonstrate that PFGE achieves 5x memory efficiency compared to previous methods, without compromising on generalization performance. For those interested, our code is available at https://github.com/ZJLAB-AMMI/PFGE.

📄 PDF Abstract BibTeX arXiv:2202.06658

Code (1)

zjlab-ammi/pfge 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

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

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

2018-02-27 · NeurIPS 2018 12 · Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry Vetrov 외

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which tra…

TabPFGen -- Tabular Data Generation with TabPFN

2024-06-07 · Junwei Ma, Apoorv Dankar, George Stein, Guangwei Yu 외

Advances in deep generative modelling have not translated well to tabular data. We argue that this is caused by a mismatch in structure between popular generative models and discriminative models of tabular data. We thus…

Data AugmentationImputationIn-Context LearningTabular Data Generation

Improved Convex Decomposition with Ensembling and Boolean Primitives

2024-05-29 · Vaibhav Vavilala, Florian Kluger, Seemandhar Jain, Bodo Rosenhahn 외

Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established vision problem. This is a good model of a difficult fitting pr…

regressionScene Segmentation

Assessing the Benefits of Model Ensembles in Neural Re-Ranking for Passage Retrieval

2021-01-21 · Luís Borges, Bruno Martins, Jamie Callan

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named F…

Learning-To-RankPassage RerankingPassage RetrievalReranking+2

Fast Hyperparameter Optimization of Deep Neural Networks via Ensembling Multiple Surrogates

2018-11-06 · Yang Li, Jiawei Jiang, Yingxia Shao, Bin Cui

The performance of deep neural networks crucially depends on good hyperparameter configurations. Bayesian optimization is a powerful framework for optimizing the hyperparameters of DNNs. These methods need sufficient eva…

Bayesian OptimizationHyperparameter Optimization