The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
复制标题
合并阶梯性质:两层神经网络稀疏函数SGD学习的必要且近充分条件
DOI:
--
复制
发表时间:
2022
期刊:
影响因子:
--
通讯作者:
T. Misiakiewicz
中科院分区:
文献类型:
--
作者:
Abbe, E.;Boix-Adsera, E;T. Misiakiewicz