In this work, a gradient-based primal-dual method of multipliers is proposed for solving a class of linearly constrained non-convex problems. We show that with random initialization …
H Fu, Y Chi, Y Liang - IEEE transactions on signal processing, 2020 - ieeexplore.ieee.org
We study model recovery for data classification, where the training labels are generated from a one-hidden-layer neural network with sigmoid activations, also known as a single …
S Lu, M Hong, Z Wang - International Conference on …, 2019 - proceedings.mlr.press
Alternating gradient descent (A-GD) is a simple but popular algorithm in machine learning, which updates two blocks of variables in an alternating manner using gradient descent …
H Fu, Y Chi, Y Liang - 2019 IEEE International Symposium on …, 2019 - ieeexplore.ieee.org
We study model recovery for data classification, where the training labels are generated from a one-hidden-layer neural network with sigmoid activations, and the goal is to recover …