arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.06302cs.LGmath.OC
收藏

无反向传播优化

Optimization without Backpropagation

École Normale Supérieure de Paris(巴黎高等师范学院)

Gabriel Belouze

摘要:

最近引入了前向梯度来绕过自微分中的反向传播,同时保留真实梯度的无偏估计。我们推导出一个最优性条件,以获得最佳近似的前向梯度,这使我们的数学见解,表明在高维优化是具有挑战性的前向梯度。我们对测试函数的大量实验支持这一说法。

英文摘要:

Forward gradients have been recently introduced to bypass backpropagation in autodifferentiation, while retaining unbiased estimators of true gradients. We derive an optimality condition to obtain best approximating forward gradients, which leads us to mathematical insights that suggest optimization in high dimension is challenging with forward gradients. Our extensive experiments on test functions support this claim.

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。

↑