We analyze the orthogonal greedy algorithm when applied to dictionaries $\mathbb{D}$ whose convex hull has small entropy. We show that if the metric entropy of the convex hull of $\mathbb{D}$ decays at a rate of $O(n^{-\frac{1}{2}-\alpha})$ for $\alpha > 0$, then the orthogonal greedy algorithm converges at the same rate on the variation space of $\mathbb{D}$. This improves upon the well-known $O(n^{-\frac{1}{2}})$ convergence rate of the orthogonal greedy algorithm in many cases, most notably for dictionaries corresponding to shallow neural networks. These results hold under no additional assumptions on the dictionary beyond the decay rate of the entropy of its convex hull. In addition, they are robust to noise in the target function and can be extended to convergence rates on the interpolation spaces of the variation norm. We show empirically that the predicted rates are obtained for the dictionary corresponding to shallow neural networks with Heaviside activation function in two dimensions. Finally, we show that these improved rates are sharp and prove a negative result showing that the iterates generated by the orthogonal greedy algorithm cannot in general be bounded in the variation norm of $\mathbb{D}$.
翻译:我们分析在应用到词典 $\ mathbb{D} $ 时的正方贪婪算法 $\ mathb{D} 美元, 其 convex 船体的 convex 船体 $\ mathbb{D} 美元 小英特罗比。 我们显示,如果在很多情况下, $\\ mathb{D} 美元 的 convex 船体的 convex 船体的公制通缩率以美元( $-\\\ mathb{D} 美元 美元, 以美元 美元 美元 的速率下降, 美元 美元 ($\\\\\\ frac{1\\\\\\\\\\\\\\} 美元 。 我们显示, 美元 美元 或 美元 美元 的正统的贪婪算法 算法, 其预测率不能以 美元为底底线 显示, 我们的直线矩阵 显示, 的直向下演算结果 。