通过随机核正则化，深度核模型在CIFAR-10上达到94.5%准确率，逼近神经网络性能。
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
- 引入训练时向学习的格拉姆矩阵加噪声的随机核正则化方法
- 在CIFAR-10上实现94.5%测试准确率，超越原有92.7%的核方法记录
- 证明深度核模型也能在复杂任务中表现优异，适合关注可解释性的研究者
近期工作提出了卷积深度核模型，在类似ResNet的架构下于CIFAR-10上实现了92.7%的测试准确率，是核方法当前最优结果。然而仍低于使用相似架构的神经网络所达的94%以上准确率。本文提出多项改进以提升卷积深度核模型的泛化能力，包括随机核正则化——在训练过程中向学习到的格拉姆矩阵添加噪声。改进后的模型在CIFAR-10上达到94.5%的测试准确率。这一发现具有重要理论与实践意义：表明在图像分类等复杂任务上表现良好并非神经网络独有；只要具备从数据中学习表征的能力，其他方法如深度核模型同样可取得卓越性能。
原文摘要 · Abstract (English)
Recent work developed convolutional deep kernel machines, achieving 92.7% test accuracy on CIFAR-10 using a ResNet-inspired architecture, which is SOTA for kernel methods. However, this still lags behind neural networks, which easily achieve over 94% test accuracy with similar architectures. In this work we introduce several modifications to improve the convolutional deep kernel machine's generalisation, including stochastic kernel regularisation, which adds noise to the learned Gram matrices during training. The resulting model achieves 94.5% test accuracy on CIFAR-10. This finding has important theoretical and practical implications, as it demonstrates that the ability to perform well on complex tasks like image classification is not unique to neural networks. Instead, other approaches including deep kernel methods can achieve excellent performance on such tasks, as long as they have the capacity to learn representations from data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。