Lingxiao Wang

Learning One-hidden-layer ReLU Networks via Gradient Descent

2018 · arXiv (Cornell University)

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher network. …

On the Global Optimality of Model-Agnostic Meta-Learning

2020 · arXiv (Cornell University)

Model-agnostic meta-learning (MAML) formulates meta-learning as a bilevel optimization problem, where the inner level solves each subtask based on a shared prior, while the outer level searches for the optimal shared prior by optimizing its …

Least squares exponential fitting of surface potential

2024

The rated currents of the ground electrodes of the 800kV, 8000MW and 10000MW converter stations built in my country in recent years are 5000A and 6250A respectively. Due to the large ground current flowing into …