连续学习中的拟牛顿方法
Continual Learning With Quasi-Newton Methods
AI总结：
针对EWC因海森矩阵简化导致的性能瓶颈，本文提出CSQN方法，利用拟牛顿法精确近似海森矩阵，在四个基准上显著降低遗忘并提升性能，优于现有方法。
摘要：
灾难性遗忘仍然是神经网络按顺序学习任务时面临的主要挑战。弹性权重巩固（EWC）试图通过引入一种基于贝叶斯启发的正则化损失来保留先前学习任务的知识，从而解决这一问题。然而，EWC依赖于拉普拉斯近似，其中海森矩阵被简化为Fisher信息矩阵的对角线，假设模型参数不相关。这种过于简单的假设常常导致海森矩阵估计不佳，限制了其有效性。为了克服这一局限性，我们引入了采样拟牛顿连续学习（CSQN），该方法利用拟牛顿方法计算更准确的海森矩阵近似。CSQN能够捕获对角线之外的参数交互，而无需特定于架构的修改，使其适用于各种任务和架构。在四个基准上的实验结果表明，CSQN始终优于EWC和其他最先进的基线方法，包括基于重放的方法。CSQN将EWC的遗忘率降低了50%，并平均提高了8%的性能。值得注意的是，CSQN在四个基准中的三个上取得了优异的结果，包括最具挑战性的场景，突显了其作为连续学习稳健解决方案的潜力。
英文摘要：
Catastrophic forgetting remains a major challenge when neural networks learn tasks sequentially. Elastic Weight Consolidation (EWC) attempts to address this problem by introducing a Bayesian-inspired regularization loss to preserve knowledge of previously learned tasks. However, EWC relies on a Laplace approximation where the Hessian is simplified to the diagonal of the Fisher information matrix, assuming uncorrelated model parameters. This overly simplistic assumption often leads to poor Hessian estimates, limiting its effectiveness. To overcome this limitation, we introduce Continual Learning with Sampled Quasi-Newton (CSQN), which leverages Quasi-Newton methods to compute more accurate Hessian approximations. CSQN captures parameter interactions beyond the diagonal without requiring architecture-specific modifications, making it applicable across diverse tasks and architectures. Experimental results across four benchmarks demonstrate that CSQN consistently outperforms EWC and other state-of-the-art baselines, including rehearsal-based methods. CSQN reduces EWC's forgetting by 50 percent and improves its performance by 8 percent on average. Notably, CSQN achieves superior results on three out of four benchmarks, including the most challenging scenarios, highlighting its potential as a robust solution for continual learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
