We propose a new algorithm for efficiently solving the damped Fisher matrix in large-scale scenarios where the number of parameters significantly exceeds the number of available samples. This problem is fundamental for natural gradient descent and stochastic reconfiguration. Our algorithm is based on Cholesky decomposition and is generally applicable. Benchmark results show that the algorithm is significantly faster than existing methods.

翻译：我们提出了一种新算法，用于在参数数量显著超过可用样本数量的大规模场景中高效求解阻尼Fisher矩阵。该问题对自然梯度下降和随机重配置至关重要。我们的算法基于Cholesky分解，具有普遍适用性。基准测试结果表明，该算法显著快于现有方法。