Kangqiao Liu

According to our database, Kangqiao Liu authored at least 6 papers between 2020 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2022

Power-Law Escape Rate of SGD.

Takashi Mori, Ziyin Liu, Kangqiao Liu, Masahito Ueda

Proceedings of the International Conference on Machine Learning, 2022

Strength of Minibatch Noise in SGD.

Ziyin Liu, Kangqiao Liu, Takashi Mori, Masahito Ueda

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Logarithmic landscape and power-law escape rate of SGD.

Takashi Mori, Ziyin Liu, Kangqiao Liu, Masahito Ueda

CoRR, 2021

On Minibatch Noise: Discrete-Time SGD, Overparametrization, and Bayes.

Ziyin Liu, Kangqiao Liu, Takashi Mori, Masahito Ueda

CoRR, 2021

Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent.

Kangqiao Liu, Ziyin Liu, Masahito Ueda

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Stochastic Gradient Descent with Large Learning Rate.

Kangqiao Liu, Ziyin Liu, Masahito Ueda

CoRR, 2020